{"cells":[{"cell_type":"code","execution_count":1,"metadata":{"executionInfo":{"elapsed":476,"status":"ok","timestamp":1720679526275,"user":{"displayName":"HUANG DONGHAO _","userId":"00977795705617022768"},"user_tz":-480},"id":"uWKRSV6eZsCn"},"outputs":[],"source":["%load_ext autoreload\n","%autoreload 2"]},{"cell_type":"code","execution_count":2,"metadata":{"application/vnd.databricks.v1+cell":{"cellMetadata":{"byteLimit":2048000,"rowLimit":10000},"inputWidgets":{},"nuid":"eb33b19f-1206-41ee-84e2-e6258a12eef7","showTitle":false,"title":""},"colab":{"base_uri":"https://localhost:8080/"},"executionInfo":{"elapsed":2534,"status":"ok","timestamp":1720679529344,"user":{"displayName":"HUANG DONGHAO _","userId":"00977795705617022768"},"user_tz":-480},"id":"xwFh14uiZBrI","outputId":"d767799c-34c2-46a5-f052-378146a55321"},"outputs":[],"source":["from pathlib import Path\n","\n","if \"workding_dir\" not in locals():\n"," try:\n"," from google.colab import drive\n","\n"," drive.mount(\"/content/drive\")\n"," workding_dir = \"/content/drive/MyDrive/logical-reasoning/\"\n"," except ModuleNotFoundError:\n"," workding_dir = str(Path.cwd().parent)"]},{"cell_type":"code","execution_count":3,"metadata":{"application/vnd.databricks.v1+cell":{"cellMetadata":{"byteLimit":2048000,"rowLimit":10000},"inputWidgets":{},"nuid":"6d394937-6c99-4a7c-9d32-7600a280032f","showTitle":false,"title":""},"colab":{"base_uri":"https://localhost:8080/"},"executionInfo":{"elapsed":5,"status":"ok","timestamp":1720679529345,"user":{"displayName":"HUANG DONGHAO _","userId":"00977795705617022768"},"user_tz":-480},"id":"G5pNu3zgZBrL","outputId":"160a554f-fb08-4aa0-bc00-0422fb7c1fac"},"outputs":[{"name":"stdout","output_type":"stream","text":["workding dir: /Users/inflaton/code/engd/projects/logical-reasoning\n"]}],"source":["import os\n","import sys\n","from pathlib import Path\n","\n","os.chdir(workding_dir)\n","sys.path.append(workding_dir)\n","print(\"workding dir:\", workding_dir)"]},{"cell_type":"code","execution_count":4,"metadata":{},"outputs":[{"name":"stdout","output_type":"stream","text":["working dir: /Users/inflaton/code/engd/projects/logical-reasoning\n"]}],"source":["# haotian comp\n","import os\n","import sys\n","from pathlib import Path\n","\n","if \"workding_dir\" not in locals():\n"," workding_dir = str(Path.cwd().parent)\n","os.chdir(workding_dir)\n","sys.path.append(workding_dir)\n","print(\"working dir:\", workding_dir)"]},{"cell_type":"code","execution_count":5,"metadata":{"application/vnd.databricks.v1+cell":{"cellMetadata":{"byteLimit":2048000,"rowLimit":10000},"inputWidgets":{},"nuid":"9f67ec60-2f24-411c-84eb-0dd664b44775","showTitle":false,"title":""},"colab":{"base_uri":"https://localhost:8080/"},"executionInfo":{"elapsed":3,"status":"ok","timestamp":1720679529345,"user":{"displayName":"HUANG DONGHAO _","userId":"00977795705617022768"},"user_tz":-480},"id":"hPCC-6m7ZBrM","outputId":"c7aa2c96-5e99-440a-c148-201d79465ff9"},"outputs":[{"name":"stdout","output_type":"stream","text":["loading env vars from: /Users/inflaton/code/engd/projects/logical-reasoning/.env\n"]},{"data":{"text/plain":["True"]},"execution_count":5,"metadata":{},"output_type":"execute_result"}],"source":["from dotenv import find_dotenv, load_dotenv\n","\n","found_dotenv = find_dotenv(\".env\")\n","\n","if len(found_dotenv) == 0:\n"," found_dotenv = find_dotenv(\".env.example\")\n","print(f\"loading env vars from: {found_dotenv}\")\n","load_dotenv(found_dotenv, override=True)"]},{"cell_type":"code","execution_count":6,"metadata":{"application/vnd.databricks.v1+cell":{"cellMetadata":{"byteLimit":2048000,"rowLimit":10000},"inputWidgets":{},"nuid":"f1597656-8042-4878-9d3b-9ebfb8dd86dc","showTitle":false,"title":""},"colab":{"base_uri":"https://localhost:8080/"},"executionInfo":{"elapsed":3,"status":"ok","timestamp":1720679529345,"user":{"displayName":"HUANG DONGHAO _","userId":"00977795705617022768"},"user_tz":-480},"id":"1M3IraVtZBrM","outputId":"29ab35f6-2970-4ade-d85d-3174acf8cda0"},"outputs":[],"source":["model_orders = {\n"," \"internlm2_5-7b-chat-1m\": 10,\n"," \"Qwen2-7B-Instruct\": 20,\n"," \"Llama3.1-8B-Chinese-Chat\": 30,\n"," \"Llama3.1-70B-Chinese-Chat\": 40,\n"," \"Qwen2-72B-Instruct\": 50,\n","}"]},{"cell_type":"code","execution_count":10,"metadata":{},"outputs":[],"source":["markers = [\n"," \"o\",\n"," \"x\",\n"," \"^\",\n"," \"s\",\n"," \"d\",\n"," \"P\",\n"," \"X\",\n"," \"*\",\n"," \"v\",\n"," \">\",\n"," \"<\",\n"," \"p\",\n"," \"h\",\n"," \"H\",\n"," \"+\",\n"," \"|\",\n"," \"_\",\n","]\n","model_markers = {k: markers[i] for i, k in enumerate(model_orders.keys())}"]},{"cell_type":"code","execution_count":9,"metadata":{},"outputs":[{"data":{"text/html":["
\n","\n","\n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n","
epochmodelaccuracyprecisionrecallf1
00.0internlm/internlm2_5-7b-chat-1m_torch.bfloat16_lf0.5106670.7432140.5106670.535733
10.2internlm/internlm2_5-7b-chat-1m/checkpoint-35_...0.7843330.7977650.7843330.786494
20.4internlm/internlm2_5-7b-chat-1m/checkpoint-70_...0.7836670.7996980.7836670.788688
30.6internlm/internlm2_5-7b-chat-1m/checkpoint-105...0.7243330.8171170.7243330.756580
40.8internlm/internlm2_5-7b-chat-1m/checkpoint-140...0.8030000.8031410.8030000.802806
51.0internlm/internlm2_5-7b-chat-1m/checkpoint-175...0.7676670.8108440.7676670.784319
61.2internlm/internlm2_5-7b-chat-1m/checkpoint-210...0.7736670.8091670.7736670.787687
71.4internlm/internlm2_5-7b-chat-1m/checkpoint-245...0.7623330.8062290.7623330.777669
81.6internlm/internlm2_5-7b-chat-1m/checkpoint-280...0.7553330.8086200.7553330.775559
91.8internlm/internlm2_5-7b-chat-1m/checkpoint-315...0.7480000.8172000.7480000.773991
102.0internlm/internlm2_5-7b-chat-1m/checkpoint-350...0.7560000.8126880.7560000.777781
00.0Qwen/Qwen2-7B-Instruct_torch.float16_lf0.6193330.7555700.6193330.672630
10.2Qwen/Qwen2-7B-Instruct/checkpoint-35_torch.flo...0.7250000.7840170.7250000.748995
20.4Qwen/Qwen2-7B-Instruct/checkpoint-70_torch.flo...0.7590000.8005300.7590000.774875
30.6Qwen/Qwen2-7B-Instruct/checkpoint-105_torch.fl...0.6926670.8039180.6926670.733248
40.8Qwen/Qwen2-7B-Instruct/checkpoint-140_torch.fl...0.7250000.7952720.7250000.747624
51.0Qwen/Qwen2-7B-Instruct/checkpoint-175_torch.fl...0.6756670.7810150.6756670.708654
61.2Qwen/Qwen2-7B-Instruct/checkpoint-210_torch.fl...0.7013330.7969560.7013330.736268
71.4Qwen/Qwen2-7B-Instruct/checkpoint-245_torch.fl...0.7326670.7922540.7326670.755402
81.6Qwen/Qwen2-7B-Instruct/checkpoint-280_torch.fl...0.6983330.7851270.6983330.729225
91.8Qwen/Qwen2-7B-Instruct/checkpoint-315_torch.fl...0.6783330.7853910.6783330.716413
102.0Qwen/Qwen2-7B-Instruct/checkpoint-350_torch.fl...0.6890000.7929720.6890000.725999
00.0shenzhi-wang/Llama3.1-8B-Chinese-Chat_torch.fl...0.2366670.7457180.2366670.339624
10.2shenzhi-wang/Llama3.1-8B-Chinese-Chat/checkpoi...0.6256670.8274140.6256670.693570
20.4shenzhi-wang/Llama3.1-8B-Chinese-Chat/checkpoi...0.7620000.7899460.7620000.766701
30.6shenzhi-wang/Llama3.1-8B-Chinese-Chat/checkpoi...0.6803330.7980300.6803330.721244
40.8shenzhi-wang/Llama3.1-8B-Chinese-Chat/checkpoi...0.7523330.8074260.7523330.773644
51.0shenzhi-wang/Llama3.1-8B-Chinese-Chat/checkpoi...0.7370000.8090590.7370000.763784
00.0Qwen/Qwen2-72B-Instruct_torch.bfloat16_4bit_lf0.7486670.8038990.7486670.761587
\n","
"],"text/plain":[" epoch model accuracy \\\n","0 0.0 internlm/internlm2_5-7b-chat-1m_torch.bfloat16_lf 0.510667 \n","1 0.2 internlm/internlm2_5-7b-chat-1m/checkpoint-35_... 0.784333 \n","2 0.4 internlm/internlm2_5-7b-chat-1m/checkpoint-70_... 0.783667 \n","3 0.6 internlm/internlm2_5-7b-chat-1m/checkpoint-105... 0.724333 \n","4 0.8 internlm/internlm2_5-7b-chat-1m/checkpoint-140... 0.803000 \n","5 1.0 internlm/internlm2_5-7b-chat-1m/checkpoint-175... 0.767667 \n","6 1.2 internlm/internlm2_5-7b-chat-1m/checkpoint-210... 0.773667 \n","7 1.4 internlm/internlm2_5-7b-chat-1m/checkpoint-245... 0.762333 \n","8 1.6 internlm/internlm2_5-7b-chat-1m/checkpoint-280... 0.755333 \n","9 1.8 internlm/internlm2_5-7b-chat-1m/checkpoint-315... 0.748000 \n","10 2.0 internlm/internlm2_5-7b-chat-1m/checkpoint-350... 0.756000 \n","0 0.0 Qwen/Qwen2-7B-Instruct_torch.float16_lf 0.619333 \n","1 0.2 Qwen/Qwen2-7B-Instruct/checkpoint-35_torch.flo... 0.725000 \n","2 0.4 Qwen/Qwen2-7B-Instruct/checkpoint-70_torch.flo... 0.759000 \n","3 0.6 Qwen/Qwen2-7B-Instruct/checkpoint-105_torch.fl... 0.692667 \n","4 0.8 Qwen/Qwen2-7B-Instruct/checkpoint-140_torch.fl... 0.725000 \n","5 1.0 Qwen/Qwen2-7B-Instruct/checkpoint-175_torch.fl... 0.675667 \n","6 1.2 Qwen/Qwen2-7B-Instruct/checkpoint-210_torch.fl... 0.701333 \n","7 1.4 Qwen/Qwen2-7B-Instruct/checkpoint-245_torch.fl... 0.732667 \n","8 1.6 Qwen/Qwen2-7B-Instruct/checkpoint-280_torch.fl... 0.698333 \n","9 1.8 Qwen/Qwen2-7B-Instruct/checkpoint-315_torch.fl... 0.678333 \n","10 2.0 Qwen/Qwen2-7B-Instruct/checkpoint-350_torch.fl... 0.689000 \n","0 0.0 shenzhi-wang/Llama3.1-8B-Chinese-Chat_torch.fl... 0.236667 \n","1 0.2 shenzhi-wang/Llama3.1-8B-Chinese-Chat/checkpoi... 0.625667 \n","2 0.4 shenzhi-wang/Llama3.1-8B-Chinese-Chat/checkpoi... 0.762000 \n","3 0.6 shenzhi-wang/Llama3.1-8B-Chinese-Chat/checkpoi... 0.680333 \n","4 0.8 shenzhi-wang/Llama3.1-8B-Chinese-Chat/checkpoi... 0.752333 \n","5 1.0 shenzhi-wang/Llama3.1-8B-Chinese-Chat/checkpoi... 0.737000 \n","0 0.0 Qwen/Qwen2-72B-Instruct_torch.bfloat16_4bit_lf 0.748667 \n","\n"," precision recall f1 \n","0 0.743214 0.510667 0.535733 \n","1 0.797765 0.784333 0.786494 \n","2 0.799698 0.783667 0.788688 \n","3 0.817117 0.724333 0.756580 \n","4 0.803141 0.803000 0.802806 \n","5 0.810844 0.767667 0.784319 \n","6 0.809167 0.773667 0.787687 \n","7 0.806229 0.762333 0.777669 \n","8 0.808620 0.755333 0.775559 \n","9 0.817200 0.748000 0.773991 \n","10 0.812688 0.756000 0.777781 \n","0 0.755570 0.619333 0.672630 \n","1 0.784017 0.725000 0.748995 \n","2 0.800530 0.759000 0.774875 \n","3 0.803918 0.692667 0.733248 \n","4 0.795272 0.725000 0.747624 \n","5 0.781015 0.675667 0.708654 \n","6 0.796956 0.701333 0.736268 \n","7 0.792254 0.732667 0.755402 \n","8 0.785127 0.698333 0.729225 \n","9 0.785391 0.678333 0.716413 \n","10 0.792972 0.689000 0.725999 \n","0 0.745718 0.236667 0.339624 \n","1 0.827414 0.625667 0.693570 \n","2 0.789946 0.762000 0.766701 \n","3 0.798030 0.680333 0.721244 \n","4 0.807426 0.752333 0.773644 \n","5 0.809059 0.737000 0.763784 \n","0 0.803899 0.748667 0.761587 "]},"execution_count":9,"metadata":{},"output_type":"execute_result"}],"source":["import pandas as pd\n","\n","perf_df = None\n","model_perf_dfs = {}\n","for model_name in model_orders.keys():\n"," metrics_csv = f\"data/{model_name}_metrics.csv\"\n"," if not Path(metrics_csv).exists():\n"," continue\n"," df = pd.read_csv(metrics_csv)\n"," model_perf_dfs[model_name] = df\n"," perf_df = df if perf_df is None else pd.concat([perf_df, df])\n","\n","perf_df"]},{"cell_type":"code","execution_count":37,"metadata":{},"outputs":[],"source":["import matplotlib.pyplot as plt\n","from matplotlib.ticker import MultipleLocator\n","\n","def plot_perf(\n"," model_perf_dfs,\n"," model_markers,\n"," x_major_locator=0.2,\n"," y_offset=0.05,\n","):\n"," fig, ax = plt.subplots(1, 1, figsize=(12, 6))\n","\n"," for model_name, perf_df in model_perf_dfs.items():\n"," # Ensure the lengths of perf_df[\"epoch\"], perf_df[\"accuracy\"], and perf_df[\"f1\"] are the same\n"," min_length = min(len(perf_df[\"epoch\"]), len(perf_df[\"accuracy\"]), len(perf_df[\"f1\"]))\n"," perf_df = perf_df.iloc[:min_length]\n","\n"," ax.plot(\n"," perf_df[\"epoch\"], perf_df[\"f1\"], marker=model_markers[model_name], label=model_name\n"," )\n","\n"," best_f1 = perf_df[\"f1\"].idxmax()\n"," ax.annotate(\n"," f\"{perf_df['f1'].iloc[best_f1]*100:.2f}%\",\n"," (perf_df[\"epoch\"].iloc[best_f1], perf_df[\"f1\"].iloc[best_f1]),\n"," ha=\"center\",\n"," va=\"bottom\",\n"," xytext=(0, 0),\n"," textcoords=\"offset points\",\n"," fontsize=10,\n"," )\n","\n"," # Set y-axis limit\n"," y_scales = ax.get_ylim()\n"," ax.set_ylim(y_scales[0], y_scales[1] + y_offset)\n","\n"," # Add title and labels\n"," ax.set_xlabel(\"Epoch (0: base model, 0.2 - 2: fine-tuned models)\")\n"," ax.set_ylabel(\"F1 Score\")\n","\n"," # Set x-axis grid spacing to 0.2\n"," ax.xaxis.set_major_locator(MultipleLocator(x_major_locator))\n"," ax.set_title(\n"," \"Performance Analysis Across Checkpoints for Models\"\n"," )\n","\n"," # Rotate x labels\n"," plt.xticks(rotation=0)\n"," plt.grid(True)\n"," # plt.tight_layout()\n","\n"," # Set legend at the right to avoid overlapping with lines\n"," plt.legend(loc=\"center left\", bbox_to_anchor=(1.0, 0.5))\n","\n"," plt.show()"]},{"cell_type":"code","execution_count":38,"metadata":{},"outputs":[{"data":{"image/png":"iVBORw0KGgoAAAANSUhEUgAABNsAAAIjCAYAAAA6BB2fAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjkuMCwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy80BEi2AAAACXBIWXMAAA9hAAAPYQGoP6dpAAEAAElEQVR4nOzdd3gU1dfA8e+W9EoS0ihJCDX0IiAdaQKCighItTd4UbCBKAKKDQs/QUUQkKoiTVGkg/SgdBI6CT0d0uvuvH9MssmmEWBJ43yeZ0h25s7s3cvuJnty7j0aRVEUhBBCCCGEEEIIIYQQd01b1h0QQgghhBBCCCGEEKKykGCbEEIIIYQQQgghhBAWIsE2IYQQQgghhBBCCCEsRIJtQgghhBBCCCGEEEJYiATbhBBCCCGEEEIIIYSwEAm2CSGEEEIIIYQQQghhIRJsE0IIIYQQQgghhBDCQiTYJoQQQgghhBBCCCGEhUiwTQghhBBCCCGEEEIIC5FgmxBC3KEZM2ZQq1YtdDodzZo1K+vuiLvw9NNP4+/vf0+u/dNPP6HRaAgPD78n1xeqLl260KhRo1K/X39/fx555JFSv9/y+Ly6H94Td+zYgUajYceOHbd9bnn8PxNCCCHEvSHBNiFEpZHzQSZns7W1pW7duowZM4bIyEiL3temTZt4++23ad++PQsXLuTjjz+26PXvZ4MGDUKj0fDOO++UdVfKtdatW6PRaPj+++/Luiv3VEJCAlOnTqVp06Y4OjpiZ2dHo0aNeOedd7h27VpZd69CCg0NZcqUKRYN+pT2e+LTTz+NRqPB2dmZ1NTUAsfPnj1r+lnwxRdf3NO+CCGEEELkpy/rDgghhKVNmzaNgIAA0tLS2L17N99//z3r16/nxIkT2NvbW+Q+tm3bhlarZf78+VhbW1vkmkINrKxbtw5/f39+/vlnPv30UzQaTVl3666MGDGCIUOGYGNjY7Frnj17ln///Rd/f3+WLVvGK6+8YrFrlycXLlyge/fuXLp0iSeffJIXX3wRa2trjh07xvz581mzZg1nzpwp626Wibt5XoWGhjJ16lS6dOlisYzOsnhP1Ov1pKSksG7dOgYNGmR2bNmyZdja2pKWllYqfRFCCCGEyEsy24QQlU7v3r0ZPnw4zz//PD/99BOvv/46YWFh/P7773d97ZSUFACioqKws7Oz2IdKRVEKzc6436xatQqDwcCCBQu4fPkyO3fuLOsu3TWdToetra1Fg4ZLly7F09OTL7/8kr1791o0Qyk5Odli17obWVlZDBgwgMjISHbs2MHPP//M6NGjeeGFF5g1axYXLlzgySefLOtulpl78by6G2XxnmhjY0O3bt34+eefCxxbvnw5ffv2tUhfhBBCCCFulwTbhBCV3kMPPQRAWFiYad/SpUtp2bIldnZ2uLm5MWTIEC5fvmx2Xs4aUAcPHqRTp07Y29vz7rvvotFoWLhwIcnJyaZpSj/99BOgBgg+/PBDAgMDsbGxwd/fn3fffZf09HSza+es87Rx40ZatWqFnZ0dP/zwg2k9oBUrVjB16lSqVauGk5MTAwcOJD4+nvT0dF5//XU8PT1xdHTkmWeeKXDthQsX8tBDD+Hp6YmNjQ1BQUGFTjXM6cPu3btp3bo1tra21KpVi8WLFxdoe/PmTcaNG4e/vz82NjZUr16dkSNHEhMTY2qTnp7OBx98QO3atbGxsaFGjRq8/fbbBfpXnGXLltGjRw+6du1KgwYNWLZsWYE2OdOF9+zZw/jx46latSoODg48/vjjREdHm7X9/fff6du3L76+vtjY2BAYGMiHH36IwWAosg+KouDv78+jjz5a4FhaWhouLi689NJLpn2zZs2iYcOG2NvbU6VKFVq1asXy5csL9DdvQOy///6jV69eeHh4YGdnR0BAAM8++2yJx2n58uUMHDiQRx55BBcXF7P7yys4OJg+ffpQpUoVHBwcaNKkCf/73/9Mx59++mkcHR05f/48ffr0wcnJiWHDhgFq0O2NN96gRo0a2NjYUK9ePb744gsURTG7j82bN9OhQwdcXV1xdHSkXr16vPvuu2ZtbjVGhVm1ahVHjx5l0qRJdOjQocBxZ2dnpk+fXmB/aGgoXbt2xd7enmrVqvH5558XaHM7z9WlS5fSunVrU987derEpk2biu37okWL0Ov1vPXWWwCEh4ebpjN+/fXX+Pn5YWdnR+fOnTlx4kSB87dt20bHjh1xcHDA1dWVRx99lJMnT5q1Kex5VZLX9E8//WQKUnbt2tX0HpazBtmdPDfv5XvirQwdOpS///6bmzdvmvb9+++/nD17lqFDhxZ6Tk6g1s3NDXt7e9q2bctff/1VoN2VK1d47LHHcHBwwNPTk3HjxhX5fhYcHMzDDz+Mi4sL9vb2dO7cmT179tyy/3f7XiCEEEKI8kmmkQohKr3z588D4O7uDsD06dN5//33GTRoEM8//zzR0dHMmjWLTp06cfjwYVxdXU3nxsbG0rt3b4YMGcLw4cPx8vKiVatWzJ07lwMHDvDjjz8C0K5dOwCef/55Fi1axMCBA3njjTcIDg7mk08+4eTJk6xZs8asX6dPn+app57ipZde4oUXXqBevXqmY5988gl2dnZMmDCBc+fOMWvWLKysrNBqtdy4cYMpU6awf/9+fvrpJwICApg8ebLp3O+//56GDRvSv39/9Ho969at49VXX8VoNDJ69GizPpw7d46BAwfy3HPPMWrUKBYsWMDTTz9Ny5YtadiwIQBJSUl07NiRkydP8uyzz9KiRQtiYmL4448/uHLlCh4eHhiNRvr378/u3bt58cUXadCgAcePH+frr7/mzJkzrF279pb/T9euXWP79u0sWrQIgKeeeoqvv/6a2bNnF5ot83//939UqVKFDz74gPDwcGbOnMmYMWP49ddfTW1++uknHB0dGT9+PI6Ojmzbto3JkyeTkJDAjBkzCu2HRqNh+PDhfP7558TFxeHm5mY6tm7dOhISEhg+fDgA8+bNY+zYsQwcOJDXXnuNtLQ0jh07RnBwcJEf9KOioujZsydVq1ZlwoQJuLq6Eh4ezurVq285RqB+qD937hwLFy7E2tqaAQMGsGzZsgIBrs2bN/PII4/g4+PDa6+9hre3NydPnuTPP//ktddeM7XLysqiV69edOjQgS+++AJ7e3sURaF///5s376d5557jmbNmrFx40beeustrl69ytdffw1ASEgIjzzyCE2aNGHatGnY2Nhw7tw5syDDnYwRwB9//AGo0yVL6saNGzz88MMMGDCAQYMGsXLlSt555x0aN25M7969AW7ruTp16lSmTJlCu3btmDZtGtbW1gQHB7Nt2zZ69uxZaB/mzp3Lyy+/zLvvvstHH31kdmzx4sUkJiYyevRo0tLS+N///sdDDz3E8ePH8fLyAmDLli307t2bWrVqMWXKFFJTU5k1axbt27fn0KFDt5z2eavXdKdOnRg7dizffPMN7777Lg0aNACgQYMGd/zcXLJkyT1/TyzKgAEDePnll1m9erUpSLV8+XLq169PixYtCrSPjIykXbt2pKSkMHbsWNzd3Vm0aBH9+/dn5cqVPP744wCkpqbSrVs3Ll26xNixY/H19WXJkiVs27atwDW3bdtG7969admyJR988AFardb0R49du3bRunXrQvt+t+8FQgghhCjHFCGEqCQWLlyoAMqWLVuU6Oho5fLly8ovv/yiuLu7K3Z2dsqVK1eU8PBwRafTKdOnTzc79/jx44perzfb37lzZwVQ5syZU+C+Ro0apTg4OJjtO3LkiAIozz//vNn+N998UwGUbdu2mfb5+fkpgLJhwwazttu3b1cApVGjRkpGRoZp/1NPPaVoNBqld+/eZu0ffPBBxc/Pz2xfSkpKgf726tVLqVWrltm+nD7s3LnTtC8qKkqxsbFR3njjDdO+yZMnK4CyevXqAtc1Go2KoijKkiVLFK1Wq+zatcvs+Jw5cxRA2bNnT4Fz8/viiy8UOzs7JSEhQVEURTlz5owCKGvWrDFrl/P/3L17d9P9K4qijBs3TtHpdMrNmzdN+wobi5deekmxt7dX0tLSTPtGjRplNo6nT59WAOX77783O7d///6Kv7+/6X4fffRRpWHDhsU+rpz+hoWFKYqiKGvWrFEA5d9//y32vKKMGTNGqVGjhqkPmzZtUgDl8OHDpjZZWVlKQECA4ufnp9y4ccPs/LxjNmrUKAVQJkyYYNZm7dq1CqB89NFHZvsHDhyoaDQa5dy5c4qiKMrXX3+tAEp0dHSR/S3JGBWmefPmiouLS4nb57xeFy9ebNqXnp6ueHt7K0888YRpX0mfq2fPnlW0Wq3y+OOPKwaDwaxt3jH08/NT+vbtqyiKovzvf/9TNBqN8uGHH5q1DwsLUwDT+1CO4OBgBVDGjRtn2tesWTPF09NTiY2NNe07evSootVqlZEjR5r25X9e5fSlJK/p3377TQGU7du3m/Xzbp6b9+o9sST3N3DgQKVbt26KoiiKwWBQvL29lalTp5rGfcaMGabzXn/9dQUw+/9PTExUAgICFH9/f9P/9cyZMxVAWbFihaldcnKyUrt2bbOxMxqNSp06dZRevXqZPS9SUlKUgIAApUePHqZ9ln4vEEIIIUT5JdNIhRCVTvfu3alatSo1atRgyJAhODo6smbNGqpVq8bq1asxGo0MGjSImJgY0+bt7U2dOnXYvn272bVsbGx45plnSnS/69evB2D8+PFm+9944w2AAtOUAgIC6NWrV6HXGjlyJFZWVqbbbdq0QVGUAtOL2rRpw+XLl8nKyjLts7OzM30fHx9PTEwMnTt35sKFC8THx5udHxQURMeOHU23q1atSr169bhw4YJp36pVq2jatKkp4yOvnPWifvvtNxo0aED9+vXNxjVnCm/+cS3MsmXL6Nu3L05OTgDUqVOHli1bFjqVFODFF180W6+qY8eOGAwGLl68WOhYJCYmEhMTQ8eOHUlJSeHUqVNF9qVu3bq0adPG7L7j4uL4+++/GTZsmOl+XV1duXLlCv/+++8tH1+OnMzJP//8k8zMzBKfB2oW2q+//srgwYNNfciZMpy3r4cPHyYsLIzXX3/dLFMTKHSNr/wFFtavX49Op2Ps2LFm+9944w0UReHvv/82eyy///47RqOx0D7fyRiBWiwj57lQUo6OjqasQwBra2tat25t9nwu6XN17dq1GI1GJk+ejFZr/utSYWP4+eef89prr/HZZ5/x3nvvFdq/xx57jGrVqplut27dmjZt2pjeO65fv86RI0d4+umnzTIqmzRpQo8ePUztilOS13RR7ua5WRhLvicWZ+jQoezYsYOIiAi2bdtGREREkVmT69evp3Xr1mZTkx0dHXnxxRcJDw8nNDTU1M7Hx4eBAwea2tnb2/Piiy+aXe/IkSOmKauxsbGm51NycjLdunVj586dxb42wHLjLYQQQojyQ4JtQohK59tvv2Xz5s1s376d0NBQLly4YPoAd/bsWRRFoU6dOlStWtVsO3nyJFFRUWbXqlatWokX/L548SJarZbatWub7ff29sbV1dUsCATqB8ui1KxZ0+y2i4sLADVq1Ciw32g0mgXR9uzZQ/fu3U3rPVWtWtU0xTB/sC3//QBUqVKFGzdumG6fP3+eRo0aFdlXUMc1JCSkwJjWrVsXoMC45nfy5EkOHz5M+/btOXfunGnr0qULf/75JwkJCQXOyd/3KlWqAJj1PSQkhMcffxwXFxecnZ2pWrWqKRiTfyzyGzlyJHv27DH9v/32229kZmaaTWt85513cHR0pHXr1tSpU4fRo0ffcp2mzp0788QTTzB16lQ8PDx49NFHWbhwYYnWttu0aRPR0dG0bt3aNEZhYWF07dqVn3/+2fShPmfq9K3+30Ct6Fi9enWzfRcvXsTX17dAsCtnymHOmAwePJj27dvz/PPP4+XlxZAhQ1ixYoVZcOFOxgjUNdkSExNv2S6v6tWrFwiE5X8+l/S5ev78ebRaLUFBQbe833/++Yd33nmHd955x7ROW2Hq1KlTYF/dunVN667ljGth0ycbNGhgCuIUpySv6aLczXOzMJZ8TyxOznqDv/76K8uWLeOBBx4ocJ95+1TU+OYcz/lau3btAs+n/OeePXsWgFGjRhV4Tv3444+kp6cX+V5j6fEWQgghRPkha7YJISqd1q1b06pVq0KPGY1GNBoNf//9NzqdrsBxR0dHs9t5M6NKqqTVAYu7dmF9K26/kr1o/fnz5+nWrRv169fnq6++okaNGlhbW7N+/Xq+/vrrAhkWt7peSRmNRho3bsxXX31V6PH8QcL8li5dCsC4ceMYN25cgeOrVq0qkGF4q77fvHmTzp074+zszLRp0wgMDMTW1pZDhw7xzjvvFJltkmPIkCGMGzfOtB7a0qVLadWqldmH7QYNGnD69Gn+/PNPNmzYwKpVq/juu++YPHkyU6dOLfS6Go2GlStXsn//ftatW8fGjRt59tln+fLLL9m/f3+B52BeOdlrgwYNKvT4P//8Q9euXYt9XPnZ2NgUyNwqKTs7O3bu3Mn27dv566+/2LBhA7/++isPPfQQmzZtQqfT3dEYAdSvX5/Dhw9z+fLlWz5/cpTk+Xy3z9XCNGzYkJs3b7JkyRJeeumlOw4aWcLdvKbv5rl5q+uWxJ2834L6HB4wYACLFi3iwoULTJky5Y6ucydy3kdmzJhBs2bNCm1T1Ljdq/EWQgghRNmTYJsQ4r4SGBiIoigEBASYMlksxc/PD6PRyNmzZ01ZEqAuyH3z5k38/Pwsen+FWbduHenp6fzxxx9mGS4lmcZZlMDAwEIrJuZvc/ToUbp161biD9Y5FEVh+fLldO3alVdffbXA8Q8//JBly5aVeDpvjh07dhAbG8vq1avp1KmTaX/eqrTFcXNzo2/fvixbtoxhw4axZ88eZs6cWaCdg4MDgwcPZvDgwWRkZDBgwACmT5/OxIkTsbW1LfL6bdu2pW3btkyfPp3ly5czbNgwfvnlF55//vlC2ycnJ/P7778zePBgs6ltOcaOHcuyZcvo2rUrgYGBAJw4cYLu3buX6PHm5efnx5YtW0hMTDTLbsuZepv3uazVaunWrRvdunXjq6++4uOPP2bSpEls377ddN93Mkb9+vXj559/ZunSpUycOPG2H0NRSvpcDQwMxGg0EhoaWmQQJYeHhwcrV66kQ4cOdOvWjd27d+Pr61ugXU4WVF5nzpwxFT3IGdfTp08XaHfq1Ck8PDxwcHAoti8lcavX6O0+N4tSmu+JQ4cOZcGCBWi1WoYMGVJsn4oa35zjOV9PnDiBoihm45X/3JzXmrOz8x291sBy4y2EEEKI8kOmkQoh7isDBgxAp9MxderUApkeiqIQGxt7x9fu06cPQIGATE4GTd++fe/42iWVk9WS97HFx8ezcOHCO77mE088wdGjRwtUDsx7P4MGDeLq1avMmzevQJvU1NRip77t2bOH8PBwnnnmGQYOHFhgGzx4MNu3b+fatWu31e/CxiIjI4PvvvuuxNcYMWIEoaGhvPXWW+h0ugIf4vM/X6ytrQkKCkJRlCLXYLpx40aB515OMKe46WNr1qwhOTmZ0aNHFzpOjzzyCKtWrSI9PZ0WLVoQEBDAzJkzuXnzptl1SpLh1KdPHwwGA7Nnzzbb//XXX6PRaEyVPePi4gqcm/+x3MkYAQwcOJDGjRszffp09u3bV+B4YmIikyZNuuVjya+kz9XHHnsMrVbLtGnTCmRBFjaG1atXZ8uWLaSmptKjR49C30vWrl3L1atXTbcPHDhAcHCwaTx9fHxo1qwZixYtMvt/O3HiBJs2bTK9x9ytnIBd/ufGnT43i1Ka74ldu3blww8/ZPbs2Xh7exfbpwMHDpg9p5KTk5k7dy7+/v6macN9+vTh2rVrrFy50tQuJSWFuXPnml2vZcuWBAYG8sUXX5CUlFTg/qKjo4vsi6XHWwghhBDlh2S2CSHuK4GBgXz00UdMnDiR8PBwHnvsMZycnAgLC2PNmjW8+OKLvPnmm3d07aZNmzJq1Cjmzp1rmsJ44MABFi1axGOPPXbb0/vuRM+ePbG2tqZfv3689NJLJCUlMW/ePDw9Pbl+/fodXfOtt95i5cqVPPnkkzz77LO0bNmSuLg4/vjjD+bMmUPTpk0ZMWIEK1as4OWXX2b79u20b98eg8HAqVOnWLFiBRs3bixyau+yZcvQ6XRFfvDu378/kyZN4pdffimw0Hpx2rVrR5UqVRg1ahRjx45Fo9GwZMmS25oi27dvX9zd3fntt9/o3bs3np6eZsd79uyJt7c37du3x8vLi5MnTzJ79myzQg/5LVq0iO+++47HH3+cwMBAEhMTmTdvHs7OzsUGU5YtW4a7uzvt2rUr9Hj//v2ZN28ef/31FwMGDOD777+nX79+NGvWjGeeeQYfHx9OnTpFSEgIGzduLPZx9+vXj65duzJp0iTCw8Np2rQpmzZt4vfff+f11183ZfNMmzaNnTt30rdvX/z8/IiKiuK7776jevXqpgXo72SMAKysrFi9ejXdu3enU6dODBo0iPbt22NlZUVISAjLly+nSpUqTJ8+vdjHkl9Jn6u1a9dm0qRJfPjhh3Ts2JEBAwZgY2PDv//+i6+vL5988kmBa9euXZtNmzbRpUsXevXqxbZt23B2djY73qFDB1555RXS09OZOXMm7u7uvP3226Y2M2bMoHfv3jz44IM899xzpKamMmvWLFxcXCw2PbJZs2bodDo+++wz4uPjsbGx4aGHHmL58uV39NwsSmm+J2q12iILU+Q1YcIEfv75Z3r37s3YsWNxc3Nj0aJFhIWFsWrVKtOU6hdeeIHZs2czcuRIDh48iI+PD0uWLMHe3r7A/f7444/07t2bhg0b8swzz1CtWjWuXr3K9u3bcXZ2Zt26dYX25U7fC4QQQghRAZRe4VMhhLi3Fi5cqADKv//+e8u2q1atUjp06KA4ODgoDg4OSv369ZXRo0crp0+fNrXp3Lmz0rBhw0LPHzVqlOLg4FBgf2ZmpjJ16lQlICBAsbKyUmrUqKFMnDhRSUtLM2vn5+en9O3bt8D527dvVwDlt99+K9Fj++CDDxRAiY6ONu37448/lCZNmii2traKv7+/8tlnnykLFixQACUsLOyWfejcubPSuXNns32xsbHKmDFjlGrVqinW1tZK9erVlVGjRikxMTGmNhkZGcpnn32mNGzYULGxsVGqVKmitGzZUpk6daoSHx9fcBCzz3F3d1c6duxY6PEcAQEBSvPmzYsdi5yx2759u2nfnj17lLZt2yp2dnaKr6+v8vbbbysbN24s0G7UqFGKn59foff96quvKoCyfPnyAsd++OEHpVOnToq7u7tiY2OjBAYGKm+99ZbZ483pb87YHzp0SHnqqaeUmjVrKjY2Noqnp6fyyCOPKP/991+Rjz8yMlLR6/XKiBEjimyTkpKi2NvbK48//rhp3+7du5UePXooTk5OioODg9KkSRNl1qxZZo+7sOexoihKYmKiMm7cOMXX11exsrJS6tSpo8yYMUMxGo2mNlu3blUeffRRxdfXV7G2tlZ8fX2Vp556Sjlz5sxtjVFxbty4oUyePFlp3LixYm9vr9ja2iqNGjVSJk6cqFy/ft3UrqjXa2H/t7fzXF2wYIHSvHlzU7vOnTsrmzdvNh0v7HUUHBysODk5KZ06dVJSUlKUsLAwBVBmzJihfPnll0qNGjUUGxsbpWPHjsrRo0cL9HnLli1K+/btFTs7O8XZ2Vnp16+fEhoaatYm//OqqL7kjE3+1/S8efOUWrVqKTqdzvR6uJPnZo579Z54u/eXV95xz+v8+fPKwIEDFVdXV8XW1lZp3bq18ueffxY4/+LFi0r//v0Ve3t7xcPDQ3nttdeUDRs2FHj/UBRFOXz4sDJgwADT89zPz08ZNGiQsnXrVlMbS7wXCCGEEKJi0CjKba6CLYQQQtxHxo0bx/z584mIiCiQ1SJESYSHhxMQEMCMGTPuOHNWCCGEEEJUHLJmmxBCCFGEtLQ0li5dyhNPPCGBNiGEEEIIIUSJyJptQgghRD5RUVFs2bKFlStXEhsby2uvvVbWXRJCCCGEEEJUEBJsE0IIIfIJDQ1l2LBheHp68s0335gqBAohhBBCCCHErciabUIIIYQQQgghhBBCWIis2SaEEEIIIYQQQgghhIVIsE0IIYQQQgghhBBCCAu579ZsMxqNXLt2DScnJzQaTVl3RwghhBBCCCFEJacoComJifj6+qLVSs6LEJXdfRdsu3btGjVq1CjrbgghhBBCCCGEuM9cvnyZ6tWrl3U3hBD32H0XbHNycgLUNzlnZ+cy7k3xMjMz2bRpEz179sTKyqqsu1PhyXhanoypZcl4Wp6MqWXJeFqejKllyXhanoypZcl4Wl5FGdOEhARq1Khh+jwqhKjc7rtgW87UUWdn5woRbLO3t8fZ2blc/+CoKGQ8LU/G1LJkPC1PxtSyZDwtT8bUsmQ8LU/G1LJkPC2voo2pLGUkxP1BJosLIYQQQgghhBBCCGEhEmwTQgghhBBCCCGEEMJCJNgmhBBCCCGEEEIIIYSFSLBNCCGEEEIIIYQQQggLkWCbEEIIIYQQQgghhBAWIsE2IYQQQgghhBBCCCEsRIJtQgghhBBCCCGEEEJYiATbhBBCCCGEEEIIIYSwEAm2CSGEEEIIIYQQQghhIRJsE0IIIYQQQgghhBDCQiTYJoQQQgghhBBCCCGEhUiwTQghhBBCCCGEEEIIC5FgmxBCCCGEEEIIIYQQFiLBNiGEEEIIIYQQQgghLESCbUIIIYQQQgghhBBCWIgE24QQQgghhBBCCCGEsBAJtgkhhBBCCCGEEEIIYSESbBNCCCGEEEIIIYQQwkIk2CaEEEIIIYQQQgghhIVIsE0IIYQQQgghhBBCCAuRYJsQQgghhBBCCCGEEBYiwTYhhBBCCCGEEEIIISxEgm1CCCGEEEIIIYQQQliIBNuEEEIIIYQQQgghhLAQCbYJIYQQQgghhBBCCGEhEmwTQgghhBBCCCGEEMJCJNgmhBBCCCGEEEIIIYSFSLBNCCGEEEIIIYQQQggLkWCbEEIIIYQQQgghhBAWIsE2IYQQQgghhBBCCCEsRIJtQgghhBBCCCGEEEJYiATbhBBCCCGEEEIIIYSwEAm2CSGEEEIIIYQQQghhIRJsE0IIIYQQQgghhBDCQiTYJoQQQgghhBBCCCGEhUiwTQghhBBCCCGEEEIIC5FgmxBCCCGEEEIIIYQQFiLBNiGEEEIIIYQQQgghLESCbUIIIYQQQgghhBBCWIgE24QQQgghhBBCCCGEsBAJtgkhhBBCCCGEEEIIYSESbBNCCCGEEEIIIYQQwkIk2CaEEEIIIYQQQgghhIVIsE0IIYQQQgghhBBCCAuRYJsQQgghhBBCCCGEEBYiwTYhhBBlwmAw8P777xMQEICdnR2BgYF8+OGHKIpiaqMoCpMnT8bHxwc7Ozu6d+/O2bNni73uJ598wgMPPICTkxPVqlXj448/5vTp02ZtIiIiGDFiBN7e3jg4ONCiRQtWrVplOp6ens6IESNwdnambt26bNmyxez8GTNm8H//938WGAUhhBBCCCFEZSPBNiGEEGXis88+4/vvv2f27NmcPHmSzz77jM8//5xZs2aZ2nz++ed88803zJkzh+DgYBwcHOjVqxdpaWlFXveff/5h9OjR7N+/n/Xr12MwGOjbty/JycmmNiNHjuT06dP88ccfHD9+nAEDBjBo0CAOHz4MwNy5czl48CD79u3jxRdfZOjQoaYgYFhYGPPmzWP69On3aGSEEEIIIYQQFZkE24QQQpSJvXv38uijj9K3b1/8/f0ZOHAgPXv25MCBA4Ca1TZz5kzee+89Hn30UZo0acLixYu5du0aa9euLfK6GzZs4Omnn6Zhw4Y0bdqUsWPHcunSJQ4ePGh23//3f/9H69atqVWrFu+99x6urq6mNidPnqR///40bNiQ0aNHEx0dTUxMDACvvPIKn332Gc7OzvducIQQQgghhBAVlgTbhBBClIl27dqxdetWzpw5A8DRo0fZvXs3vXv3BtQMsoiICLp37246x8XFhTZt2rBv374S309KSgoAbm5uZvf966+/EhcXh9Fo5JdffiEtLY0uXboA0LRpU3bv3k1qaiobN27Ex8cHDw8Pli1bhq2tLY8//vjdPnwhhBBCCCFEJaUv6w4IIYS4P02YMIGEhATq16+PTqfDYDAwffp0hg0bBqjrqgF4eXmZnefl5WU6ditGo5H58+fTrl07GjVqZNq/YsUKBg8ejLu7O3q9Hnt7e9asWUPt2rUBePbZZzl27BhBQUF4eHiwYsUKbty4weTJk9mxYwfvvfcev/zyC4GBgSxYsIBq1apZYkiEEEIIIYQQlYAE24QQQpSJFStWsGzZMpYvX07Dhg05cuQIr7/+Or6+vowaNcoi9zF27FguXrxIcHCw2f7333+fmzdvsmXLFjw8PFi7di2DBg1i165dNG7cGCsrK7799luzc5555hnGjh3L4cOHWbt2LUePHuXzzz9n7NixZsUVhBBCCCGEEPc3CbYJIYQoE2+99RYTJkxgyJAhADRu3JiLFy/yySefMGrUKLy9vQGIjIzEx8fHdF5kZCTNmjW75fXHjBnD+vXr+eijj6hevbpp//nz55k9ezYnTpygYcOGgDptdNeuXXz77bfMmTOnwLW2b99OSEgIP/74I2+99RZ9+vTBwcGBQYMGMXv27LsZBiGEEEIIIUQlI2u2CSGEKBMpKSloteY/hnQ6HUajEYCAgAC8vb3ZunWr6XhCQgLBwcE8+OCDRV5XURTGjBnDmjVr+Hz+Cq7ovAkOi8NgVEz3CxR733mlpaUxevRofvjhB9N018zMTAAyMzMxGAx38OiFEEIIIYQQlZUE24QQQpSJfv36MX36dP766y/Cw8NZs2YNX331lan4gEaj4fXXX+ejjz7ijz/+4Pjx44wcORJfX18ee+wx03W6detmll02evRoflq8BNc+b/D2H+dZeDiBp77ZTLuP/mbDievUr1+f2rVr89JLL3HgwAHOnz/Pl19+yebNm82um+PDDz+kT58+NG/eHID27duzevVqjh07xuzZs2nfvv09HSchhBBCCCFExSLTSIUQQpSJWbNm8f777/Pqq68SFRWFr68vL730EpMnTza1efvtt0lOTubFF1/k5s2bdOjQgQ0bNmBra2tqc/78eWJiYky3v//+ewBCf3zD7P5S+7zOKykK3w9vwfr165kwYQL9+vUjKSmJ2rVrs2jRIvr06WN2zokTJ1ixYgVHjhwx7Rs4cCA7duygY8eO1KtXj+XLl1tyWIQQQgghhBAVnATbhBBClAknJydmzpzJzJkzi2yj0WiYNm0a06ZNK7JNeHi46XuDUaHtx1u4Hp9WZPup60LZ/c5DJSpq0KhRI86ePWu2T6vV8t133/Hdd9/d8nwhhBBCCCHE/afMp5F+++23+Pv7Y2trS5s2bThw4ECx7WfOnEm9evWws7OjRo0ajBs3jrS0oj9UCSGEuH8cCIsrNtCmANfj0zgQFld6nRJCCCGEEELcV8o0s+3XX39l/PjxzJkzhzZt2jBz5kx69erF6dOn8fT0LNB++fLlTJgwgQULFtCuXTvOnDnD008/jUaj4auvviqDRyCEEKI8ORWRUKJ2Ly89SIuartT3caa+txMNfJyp5eGAXlfmf4MSQgghhBBCVHBlGmz76quveOGFF3jmmWcAmDNnDn/99RcLFixgwoQJBdrv3buX9u3bM3ToUAD8/f156qmnCA4OLvI+0tPTSU9PN91OSFA/iGVmZpqqyZVXeavdibsn42l5MqaWJeN5505cTWD+nnDWn4goUfv41Ey2n45m++lo0z4rnYY6no7U83aivpcj9b2dqOfthLuD9b3qdoUjz1HLkzG1LBlPy5MxtSwZT8urKGNa3vsnhLAsjaIoSlnccUZGBvb29qxcudKs+tuoUaO4efMmv//+e4Fzli9fzquvvsqmTZto3bo1Fy5coG/fvowYMYJ333230PuZMmUKU6dOLfRa9vb2Fns8QgghSpdRgdCbGrZf03AuITcjTa9RyFIANIWcpeBiDSNrG4hI1XAtRcPVZA3XUyDdWFh7cLZS8LVX8LUHXwf1ey870EsSnBBCCCFKKCUlhaFDhxIfH4+zs3NZd0cIcY+VWWZbTEwMBoMBLy8vs/1eXl6cOnWq0HOGDh1KTEwMHTp0QFEUsrKyePnll4sMtAFMnDiR8ePHm24nJCRQo0YNevbsWe7f5DIzM9m8eTM9evTAysqqrLtT4cl4Wp6MqWXJeJZMeqaB349eZ/6ei1yISQZAr9XQt7E3z7b343JcKv/3y1FAXaMthyb73+kDmtKrofnPHqNR4crNVE5HJHEqIpFTkYmcjkji0o0UEjI1JMRrOBWf216v1RBY1SE7+82R+l5qFlxVR2s0msKDdpWBPEctT8bUsmQ8LU/G1LJkPC2vooxpzgwrIcT9oUJVI92xYwcff/wx3333HW3atOHcuXO89tprfPjhh7z//vuFnmNjY4ONjU2B/VZWVuX6zTivitTXikDG0/JkTC1LxrNwcckZLN1/kcX7wolJygDAyUbP0DY1ebq9Pz4udgA0rQl6vY6p60LNiiV4u9jyQb8gHm7kU+j1A72sCfRyoU/T3H3J6VmciUzk5PVETkUkcOp6IicjEkhMy+J0ZBKnI5PgaG57NwdrGvg4Ud87dy242p6O2FrpLD8gZUieo5YnY2pZMp6WJ2NqWTKellfex7Q8900IYXllFmzz8PBAp9MRGRlptj8yMhJvb+9Cz3n//fcZMWIEzz//PACNGzcmOTmZF198kUmTJqHVypweIYSobMJikpm/+wIrD14hLdMIQDVXO55p78/gB2rgZFvwl9eHG/nQI8ibfeei2LQrmJ4d2/BgbU902tvLOnOw0dO8ZhWa16xi2qcoCldvpnIqOwB3MiKRk9cTCI9JJi45gz3nYtlzLtbUXqfVUMvDIU8xBjUI5+1sW6mz4IQQQgghhLhflVmwzdrampYtW7J161bTmm1Go5GtW7cyZsyYQs9JSUkpEFDT6dRsgTJaek4IIcQ9oCgK/128wbydF9h8MpKct/jG1Vx4oVMt+jTyvmXlUJ1WQ5sAN2JPKrQJcLvtQFtRNBoN1avYU72KPd2DcqejpmYYOBuVaMp+O3k9gVMRidxMyeRsVBJno5JYlycLzsXOypT9lpMNV9fLCTvrypUFJ4QQQgghxP2mTKeRjh8/nlGjRtGqVStat27NzJkzSU5ONlUnHTlyJNWqVeOTTz4BoF+/fnz11Vc0b97cNI30/fffp1+/fqagmxCidBiMCsFhcRyM0eAeFndHWUNC5JdlMLIxJJJ5uy5w5PJN0/5u9T15oVMt2gS4ldtsMDtrHU2qu9Kkuqtpn6IoRCakczJnCur1BE5FJHA+Opn41EyCw+IIDosztddoIMDdgQbZWXA52XDVq9iV28cthBBCCCGEMFemwbbBgwcTHR3N5MmTiYiIoFmzZmzYsMFUNOHSpUtmmWzvvfceGo2G9957j6tXr1K1alX69evH9OnTy+ohCHFf2nDiep71sHQsPvsfPrdYD0uI4iSnZ7Hiv8ss2BPG5bhUAKz1Wp5oUY3nOgRQ29OpjHt4ZzQaDd4utni72NK1nqdpf3qWgXNRSepacNkZcCevJxCbnMGFmGQuxCTz1/HrpvZONnrq56wFl/21nrcTjjYVaulVkY/80UIIIYQQonIq89/Sx4wZU+S00R07dpjd1uv1fPDBB3zwwQel0DNRmcgHGsvZcOI6ryw9RP6J2xHxabyy9BDfD28hATdRYlEJafy0N5yl+y+SkJYFQBV7K0Y86M+Itn5UdSpY4KYysNHraOjrQkNfF7P90Ynppuw3dTpqIueiEklMz+Lf8Bv8G37DrL2fu72aAeftbFoLrkYVe7Ty/lbuyR8thBBCCCEqrzIPtglxr8kHmpJTFAWDUSHLqJBhMJJlUMg0GLM3hfRMA++tPVEg0AagABpg6rpQegR5SzBTFOt0RCLzdl3g9yNXyTSoz6gADwee6xDAEy2q37frllV1sqGqU1U61a1q2peRZeRCTJJpLbic6ahRielcjE3hYmwKG0Nyiw3ZW+uoly8AV8/bCedCCkncDvmjheXIHy2EEEIIISo3CbaJSq2sPtAYjGqQKsuokJllJNOoBquy8gSu8n7NH9TKMhrJyMo+31D4uVlGJbuNkcwspcB9/PLGoyTHXi/Qt2rtHsWn4yD++2xYoX33eHQCDvU73PIxxm6cTdKRDVR56AWcH3gUUANu4adP8GCnDzlz4gg6nY4nnniCr776CkdHRwDi4uIYNWoU27dvp06dOixYsIDmzZubrjt69Ghq1arFG2+8cQcjL8ozRVHYcy6WubsusPNMtGn/A/5VeL5jLbo38JLgTSGs9Vp1+qi3M49RzbQ/Nimd0xFq9tup6wmcjEjgTGQSKRkGDl+6yeFLN82uU83VzhR8y5mO6u/uUKIxlz9alIyiKGQaFNKyDKRnGknPMpCW72tquoEJq4/LHy2EEEIIISoxCbaJSstgVJi6LrTIDzQAb/x2lP0X4rKzuYxkZKlf8wfC1CyvvEGyvIG0gu2M5aA4bpWhX1DFaDTdzoi5SNSv75Hl14YooyPVRy8xa594dAMJB1ZjV6ul2X6dVoNeq8Fap8WoKCRnGEg5s5f0a6fRObqZtc1KjCXq1/fwaP8wv/29DVe9gddff52nn36alStXAjB9+nQSExM5dOgQ33//PS+88AL//fcfAPv37yc4OJhvvvnmXgyJKCMZWUb+PHaNuTsvcCoiEQCtBno38mHNhMdYeeUyK/Od8+qrr/LWW28REBBQ6DVXrFjBk08+WeixKVOm8Msvv3D58mWsra2pWbMmHh4etG/f3qzdX3/9xbRp0zh27Bi2trZ07tyZtWvXAhUjKOzuaEO72ja0q+1h2pdlMBIem8xJUzEGNRB3LT6NqzdTuXozlS0no0ztba201PMyXwuugY8TrvbWpjYVMQvLaFRIz1KDW+lZRtIyC/maaSz6WJZ5gCwncFZs+0wjaVkG7rY4ugJcj0+jzfQtVHezx9PJBk9nGzydbAt87+5oIwE5IYQQQohySIJtotI6EBaXnYVRtOR0Az/tDb/nfdFowEqnxUqrwUqvRa/VYq3ToNdpsdJpsNJp0Wd/tdJqsdJr0Gu16u08x63ztss+ptdqsdZr0Ws1+drnfm+l0zLns/cJrunPyg9fwNpKZ3Y/1jotfbrOoMngQXz3Uf/cc7Vas7Wf9p2P5cmv/iRu8w94DppG1MqpZo8z9fy/oNWT0HIkL/x+ncCqDrQe/g4zX32UM2fOUrduHU6ePMmQIUOoW7cuL774InPnzgUgMzOTl19+mR9//FGqC1cS8amZ/HzgEgv3hBGZkA6oUxwHtarBs+0DqOluz5SeBzEYDKZzTpw4QY8ePXjyySepUaMG16+bZ2fOnTuXGTNm0Lt37yLvt27dusyePZtatWqRkJDAW2+9RZ8+fTh37hxVq6rTM1etWsULL7zAxx9/zEMPPURWVhYnTpwwXaOiBoX1Oi21PZ2o7elEv6a+pv3xKZmcikgwBeBORiRyOiKBtEwjR6/Ec/RKvNl1fFxsqe/tRF1vJ349cPmOs7AyDcbsQJSBtJyv+TK9zANWOYGugoGx4rLF0rIDZzmBsQyDsUBfyoKNXoutlQ4bvRYbKy22eh2pmQau3Ei95bkxyRnEJGcU20arUYOunk45m60ajHO2zd3nbEtVRxus9dpiryWEEEIIISxHgm2i0opKLD7QlqN7A0+CfJwLDVAVDHBlB7K0WqyLDYiZX6esMw8yMjJ46q/VjB8/nraBHgWOHzx4kJDjx5g753uzjJb8Wvm5krhhJi5tBmBd1a/AccWQiU6vp1NdT/ZfiOV8dDKnbqhrSfV+dx5Dh4/ErUYdtmzdyvPPP8/GjRtp0qQJAJ9//jldunShVatWFnrUoqxcjkth4Z5wfv33EskZaiDN08mGUe38GdamptlzLCf4lePTTz8lMDCQzp07q5U8vb3Njq9Zs4ZBgwaZpiUXZujQoabvMzMzefbZZ9myZQvHjh2jW7duZGVl8dprrzFjxgyee+45U9ugoCDT95UtKOxib0WbWu60qeVu2mcwKlyMTTZlv53Mroh65UYq1+PTuB6fxvbT0cVcNTcLq8uM7eh12gLZXoZykOar02qw1WuxyQ565Qa/8t3O833uPh22VnmOZQfMbKzyHsv9mve6NnotGk3B9/5952N5at7+W/Z72qMN8XSyJToxjajEdKIS0onK+T4xndikdIyKWlQjOjGdkFtcr4q9lSkYV9Wp8Ew5T2cb7K3lV0MhhBBCiLslv1GJSsvTybZE7Z7rUIsHA91v3bACW7t2LTdv3uTpp58u9Pj8+fNp0KAB7dq1K/Y6X8z4nEAvZ+Ja9if/R0gNYFezCQk75tMkbidfv/MqG4+EM/nNrwGIi45kyf6LGO3bk7D3e9x8auDn58/CH3/g7NmzLFq0iH379vHyyy+zadMmWrVqxbx583BxcSnQD1E+Hbtyk7k7L/D3iQhTkKWelxPPdwygfzNfbPTFB6cyMjJYunQp48ePLzRIcfDgQY4cOcK3335b4j5lZGSwadMmXFxcaNq0KQCHDh3i6tWraLVamjdvTkREBM2aNWPGjBk0atQIgKZNm7Jt27ZKHRTWaTXUqupIraqO9GmcOw00IS2TM9nZbxuOX2fP+dhbXutyCTK1rPMFtIoPbmV/tdKZBcpKEiDLG0yz1at//ChPWge44eNiS0R8WqEZgxrA28WWYW38iv1DTZbBSGxyhnkQLl9ALjohjeikdDINCjdSMrmRksnpyMRi++doo8fTKTsg52yLVyEBuapOtjjb6gt9nQohhBBCCAm2iUos5wNNUVNJcz7QtA5wK/R4ZTJ//nx69+6Nr69vgWOpqaksX76c999/v9hrHDx4kP/9738cOnSIY3Eapq4L5XKe494utnww/HHiurkyfvx4Jk6ciE6nY+zYsSy5dIL+D9TEvXUNNodGou37JgCJwNCVV0lc9T7DX3ybHxYs4sKFC5w+fZoXXniBadOm8eWXX1pwJISlGY0K205FMXfXBQ6ExZn2d6jtwQudatGpjkeJP5BbKigM8OeffzJkyBBSUlKoUqUKf//9Nx4ealbnhQsXAHVtt6+++gp/f3++/PJLunTpwpkzZ3Bzc2PChAm88sorBAYG4u/vz/z58++boLCzrRWt/N1o5e9G7aqOJQq2vdunAc1rupqyvnKzv9Tgl7XOfEr6/Uyn1fBBvyBeWXoIDZgF3HJG6IN+QbfMiNbrtHg52+LlbAsU/fwzGhVupmaqQbiE9OxAnPp9dKJ5oC4100BSehZJ6VlciEku9v5t9FrzIFzOlNV8U1rd7K1L7f9eKuYKcf+R170QorySYJuotHI+0Ly89FCBY7fzgaaiu3jxIlu2bGH16tWFHl+5ciUpKSmMHDmy2Ovs2rWLqKgoatasadpnMBi4uX0+Nqf/ZvelS+pYNhrK0KFDiYyMxMHBAY1Gw1dffUWPNk14ckATPnpM4cjlG2wMiWRjSAQh238nxWjNbzE+RK9ZQL0W7fhp32U69+rH7C8+tuhYCMtJyzSw+tBVftx9gQvR6odyvVZD/6a+PN+xFkG+zrd9TUsEhXN07dqVI0eOEBERwZQpUxg6dCjBwcF4enpizC4cMmnSJJ544gkAFi5cSPXq1fntt9946aWXcHFxYfny5WbXfOihh5gxYwbLli27b4LCJc3Ceq5DQKV/L7Wkhxv58P3wFnkqvKq870GFV61Wg5uDNW4O1tT3LrqdoigkpWcRlZhOZEKaGogrImsuMS2L9Cwjl+NSuRxXfFajXqvBwzEnOy7venLm01g9HK3vKgtRKuYKcf+R170QojyTYJuo1NrWckev1ZCVb92ge/GBprxauHAhnp6e9O3bt9Dj8+fPp3///gXWzspvxIgRdO/e3Wxfr169aNu2LVOnTi3wQdvLywuABQsWYGtrS48ePQA1CNrSz42Wfm4838qdFrOe4fUZSwiO0rDVaCQ8OoHp60+ScuYwaREJfLXpND0betPQ11mmLJUDsUnpLNl/kSX7LhKbvXi7k62eoW1q8nQ7f3xc7O7oupYKCudwcHCgdu3a+Pn58X//93+8+eabzJ8/n4kTJ+Ljo77u867RZmNjQ61atbh06VKh11u4cCGurq48+uijDBgwgMceewwrKyuefPJJJk+efJuPtuKwVBaWKOjhRj70CPJm37koNu0KpmfHNmWakaHRaHCytcLJ1orAqkWviQhqsN08EJc7dTXndnRiOrHJGWQZFSIS0ohIKH4dVY0G3B2sqWqWKVcwKFfVyQZbK/Mp6RWxYm5FIVlDoryS170QoryTYJuo1FYevEKWUaG+txOTetdl8+4DZf6BpjQZjUYWLlzIqFGj0OsLvtzPnTvHzp07Wb9+faHn169fn08++YTHH38cd3d33N3dYfsnoNVB57exsrLC1dWVevXqqSf88zmzV+2m3dNTcHR0ZPPmzbz11lt8+umnuLq6Frj+uHHjmPD2m4wZ3BGA9+L6seznXwnq9BDbj25E51WPb7ad45tt56jmakePIC96NvSitb9buVuHqbK7EJ3Ej7vDWHXwCulZamZYNVc7nu0QwOAHauBoc3c/TiwVFC6K0WgkPV2tiNqyZUtsbGw4ffo0HTp0ANTCB+Hh4fj5FSz8ER0dzbRp09i9ezegZnRmZmaazstbTbUyKs0srPuNTquhTYAbsScV2gS4VZifS7ZWOmq621PT3b7YdpkGIzFJalZcZJ6AXHS+Ka0xSRkYjAoxSRnEJGVw8nqxl8XZVq+uJ+dsQ1VHGzaHRhZZMRfggz9CeDDQAxt9+ShaVFFI1pDlSfDy7hiNCmlZBpLSsnj/95A7rpQthBClQYJtotJSFIXlwWqWyogH/Whby524UxXrA83d2rJlC5cuXeLZZ58t9PiCBQuoXr06PXv2LPT46dOniY+PN9+p1cH26QUb//M5bJ/OgdO1+aBHD5KSkqhfvz4//PADI0aMKNB848aNnDt3jiVLlpj2vfvWOM6EHGXDFy/SumUrRk36iODrBv45E83Vm6n8tDecn/aG42pvRbf6auCtU52q2FlXnKqQFYmiKPwbfoN5uy6w5WQkSvZvtU2qu/BCx1r0buRtkaCnJYPCycnJTJ8+nf79++Pj48OWE1t478v3iLsax5NPPgmAs7MzL7/8Mh988AE1atTAz8+PGTNmAJja5PX666/zxhtvUK1aNQDat2/PkiVL6NmzJ3PnzqV9+/Z3PQblXXnLwhIVg5VOi4+L3S0zXg1GhbjkDFOmXHQxRR8ysowkpGWRkJbEuaikEvUjMiGdplM3mW5rNeqad1ZaDVZ6bXZlcU1u5XGteRVyvda8Ornp3HzVx/U6TaHnWunV9mZttXnOyds25/vsNtZ69atep829f63mnmd6S9aQ5VXW4KXBqJCWaVC3LCOpGYbc25lGUrO/T800kJ79Ne/+nHZppmMGUjONedoa1GtmGcnI/mPfreRUyj4QFlfpi6AJIcovCbaJSmvf+VguxCTjYK3j0WbVoNC/f1VuPXv2RFGKftwff/wxH39c9LpohZ7b+W316/bpnF8wgT8Tg9Du+gJ2fgpdJ7F4ytsl6luvXr3o1auX2T57e3tWrFhhtu8ZIDXDwO5zMWwKiWDLyUhupGSy6tAVVh26gq2Vlk51qtKzoTfd6ntSxcG6RPcvipZlMLIhJIJ5u8I4evmmaX/3Bp680LEWrQPcLPpBz5JBYZ1Ox6lTp1i0aBExMTFoHbVY+VnR6eNOZtNGZ8yYgV6vZ8SIEaSmptKmTRu2bdtGlSpVzK5dWFB4zJgx/Pfff7Rp04bWrVvzwQcf3O0QVAgVNQtLlH86rYaq2RVQGxbTTlEUElKzTMG3yIQ0dpyO5o+j127r/owKZGQZyQDIqJiZqfmDdTm3cwJ1uQG8/IE6Ldb63ACilVaLlV6TJ+CoZv79tCe82GzBCauPk2VQsoOVGnRa9Ro6rRq0VG+rX3O/z9s2zzm6PG01mkpZTKW0g5d5A2CpeYJZaUUGuwykZhhJy8oXKMswkJaVG+xKy3s7u02GoWQBsLIQlVj89HUhhLiXNEpxn8QroYSEBFxcXIiPj8fZ+fYX8M7h7+/PxYsXC+x/9dVX+fbbbwHYt28fkyZNIjg4GJ1OR7Nmzdi4cSN2doX/hXfnzp3MmDGDgwcPcv36dX777TesrKzo06cPVlZWpnYnT57knXfe4Z9//iErK4ugoCBWrVplWrh+/Pjx/PTTTzg4OPDpp58ybNgw07m//fYbixcvZt26dXf82CuK0csO8dfx6wxvW5OPHmtMZmYm69evLzCe4jYlRUH4Ltg7G64dQkGDBgW6TsoNxN1DWQYj/128wabsAgtXb+Yuzq3Tamjt70bPhl70CPKiepXipziVN2X9HE1Oz2LFf5eZvzuMKzfUcbXWa3miRXWe6xBAbc/i13Eqb/Zc3cPLW1423Z7TfQ7tq1X+LLR7qayfo5WRjOnd2Xc+lqfm7b9lu0XPPkDzmlXIMihkGYxkGhUys4xkGY1kGhSyDAoZBiNZBiNZxpzvi2qrfs00qm0yDbn7c8/NPpbv3EzT/rznqueZ9SHne6OCwXhf/aqORkPBAF7eIJ3OfL9WUzDAV+A8XW6wT6vJe51igoE6NfiXe7uIYGG+9vnvUwM8t+hfYpIyinzMbg7WfPxYIzKMiimglTcAlpphIN0U5CqYFWaePVZ2ATBrvRY7Kx22VmolajsrHTZWOuzy3LY1bVrT7bzn5G1nZ63FRp/zvQ5bvRY7ax2HL91k2I/Bt+zPzy+0LVeZbZb6HCqEqBgks+0O/fvvv2br9Jw4cYIePXqYpiDt27ePhx9+mIkTJzJr1iz0ej1Hjx5Fqy16ylVycjJNmzbl2WefZcCAAYW2OX/+PB06dOC5555j6tSpODs7ExISgq2tLQDr1q1j+fLlbNq0ibNnz/Lss8/Sq1cvPDw8iI+PZ9KkSWzZssWCI1E+RSWksTEkAoBhbQquwSRuQ3IMhO9WA2zhuyH6lNlhTc7fac9tAdeaEPQYWNnes+7odVra1nKnbS133n+kAaHXE9gUEsmm0EhOXk9g34VY9l2IZeq6UBr6OtOroTc9G3pRz8tJCiwUITIhjZ/2hrNs/0US0rIA9Rf/EW39GPGgHx6ONmXcw9tnMBqYHmw+3fnd3e8yvMFwPOw8qGpflap2VXG3c8fN1g2tRtYAFKIiKmnF3A61q1bYbEyjUSHLWHygLiMrJ2CXJ6iXJ5CYt22B4GB2MFBtp3AmMpHd52Ju2a9ADwdcHayzA4Lq+Ybs4GCW6asx97Yh+6uS264wikL2Y1CA8ps1ZUlxyRm8vOzQPbl23gBYccEum9sMgNlZm7ez0etK7TXWtpZ7iV73rQPcSqU/QghRGAm23aH8i3R/+umnBAYG0rlzZ0Bd+H3s2LFMmDDB1Ma0iHwRevfuTe/evYttM2nSJPr06cPnn39u2hcYGGj6/uTJk3Tp0oVWrVrRqlUrXn/9dcLCwvDw8ODtt9/mlVdeMWXAVWYr/rtMllGhpV8VGvjIX45uS0ocXNwDYbvUAFtUaME2Xo3Byg6uHMjNbLscrG4bJkCzYdDyGfCofU+7qtFoaOjrQkNfF8b1qMvluBQ2hkSwKTSS/8LjCLmWQMi1BL7afIaabvb0DPKiVyNvWtSsUmE/dFnSqYgE5u0M44+jV7M/1ECAhwPPdQjgiRbVK+RaeIqisP3ydmb8O4MrSVfMjsWlxfHN4W8KnKPT6HC3dcfdzt0sCFfVrioedh6m4JyHnQc2uooXeBSiMrsfKuZqtRqss9dvKw37zseWKNj20eON7yprSFHyB+byBegM5vsNhQXwTF+NBdpnGRVToNJgNBa8H0MR+41GDEYKHjMUc62i7sugkJSeRXxq5i3Hw8/NHh9X2wIBsAKBsjwZXrb64gNgtnpdpZyWez+87oUQFZ8E2ywgIyODpUuXMn78eDQaDVFRUQQHBzNs2DDatWvH+fPnqV+/PtOnTzdVvrsTRqORv/76i7fffptevXpx+PBhAgICmDhxIo899hgATZs2Ze7cudy4cYMLFy6QmppK7dq12b17N4cOHeK7776z0KMuvwxGhZ8PXAZgeNvKH1i8a6k34OI+NbAWtgsiT1BgfTvPhuDfAQI6gl97+PdH2D4dQyd1zbZHbA6g2z8bbJzV6+2brW4BnaHVs1C/L+ju/fSoGm72PN+xFs93rEVsUjpbT0axKTSCnWdjuBSXwo+7w/hxdxjuDtZ0b+BFr0ZetAv0wNaq4gWV7pSiKOw+F8PcnRfYdTb3w1Rrfzee7xhA9wZeFfIXc0VR2H11N98e+ZaQ2JBC22jQ4GLjQpB7ELGpsUSnRnMj7QYGxUBUahRRqVGcjDtZ7P04WTuZB+Fyvrf3MNvvbO0smZRClBKpmGtZJc0WvNusIU329E99Jf8RXNKpzp8+0aRcTXks7+R1L4Qo7yTYZgFr167l5s2bPP300wBcuHABgClTpvDFF1/QrFkzFi9eTLdu3Thx4gR16tS5o/uJiooiKSmJTz/9lI8++ojPPvuMDRs2MGDAALZv307nzp3p1asXw4cP54EHHsDOzo5Fixbh4ODAK6+8wk8//cT333/PrFmz8PDwYO7cuTRsWNxSxBXTjtNRXL2ZShV7K3rLD9qC0uJzg2vhu+D6MQoE16rWB/+OaoDNvwM4eOQey646StdJ7KvVjv/tmIx7l2l0sHNR9zceBOkJcGYjhP2jbo5e0HwEtBylTjUtBe6ONgx6oAaDHqhBcnoWu85GszEkkq0nI4lNzuDX/y7z63+XsbfW0aVeVXoGedO1vicudpVzzaSMLCPrjl5j3q4LnIpIBNSKfL0b+/BCx1o0q+Fath28Q4qiEBwRzLeHv+VI9BEArLXWZBgLro2joHAz/SYjg0aa1m7LMmYRlxZHdGq0GoBLiSY6NZqY1BhiUmPM9mcYM0jMSCQxI5EL8ReK7Ze11rrQIFz+4JybrRt6rfwoFuJuScVcy5GsIcsqreDl/Uhe90KI8kx+w7eA+fPn07t3b3x9fQE1Aw3gpZde4plnngGgefPmbN26lQULFvDJJ5/c0f3kXPfRRx9l3LhxADRr1oy9e/cyZ84c0xTWKVOmMGXKFNN5U6dOpXv37lhZWfHRRx9x/Phx/vzzT0aOHMnBgwfvqC/l2dL9auGKJ1vVuK8yloqUngiX9udmrl0/Akq+NVDc66hZa/4d1CCbo2fR1zMaoOsklE5vMevPIUQbo5l1ZBbtH/lF/SXcaICuE+HmJTi4CA4thqRI2PUF7PoS6vRUs93q9ABt6fz/ONjoebiRDw838iHTYORAWBybsqebXo9PY/3xCNYfj0Cv1fBgoDs9g7zoEeSNt8u9W3uutMSnZrI8+BI/7Q0jMiEdAHtrHYNa1eC5DgHUcKtYRSTyOhh5kNmHZ/Nf5H8A2OhsGFx3MMERwZy5cQalkI81GjTMOjyLdr7t1KwKrR5Pe0887Yt5zpNdBTEjwZQRlz84l3d/YkYiGcYMriVf41py8VUSNWioYlvFLCCXd9pq3gCdvVXF/b8SojRIxVzLkawhy5Hg5b0lr3shRHklwba7dPHiRbZs2cLq1atN+3x81F9AgoKCzNo2aNCAS5culfjaqYcPU2/jJpJ0eqo80hcPDw/0en2h1929e3eh1zh16hRLly7l8OHDLFiwgE6dOlG1alUGDRrEs88+S2JiIk5OTiXuU3l3OS6FHWeiAXiq9X06hTQjOTe4Fr4brh4CxWDexq2WGlQL6KROC3W+jV+au04EYO/VPYTGqeu5hcaFsvfaXtrnrUbqWhO6vQ9dJsCpv+C/BWqW29mN6uZSA1qMghYjwMn7bh91iVnptLSv7UH72h5M6d+Q41fjTZVNz0YlsetsDLvOxvD+7yE0reGqrvPW0IvanhXrdXI5LoUFe8JY8e9lkjPU/39PJxuebu/PsNZ+uNhX3Ay+Y9HHmH14Nvuu7wPASmvFk3Wf5PnGz+Ni40LPlT0LDbSBmt0WkRxBpjETa511ie9To1GnoLrYuFDLtVaxbdMN6WpWXEp0weBcarRpf2xaLAbFQFxaHHFpcZy+cbrY69rr7QsNwpm+t1e/d7VxvWcFH4Ijgvlfwv9wj3CnQ407XxZBCFH+SdaQ5UjwUggh7j8SbLtLCxcuxNPTk759+5r2+fv74+vry+nT5h+czpw5c8sCCHkl/LoCnV5P1NSpOD3YFmt3dx544IFCr+vnV7DipqIovPTSS3z11Vc4OjpiMBjIzFQXaM35mreiamXw84FLKAp0rONBgIdDWXendGSmqoUJwnKCawfBmG8hXle/7My1Tmr2mku1u7rLDEMG7+15z3Rbg4ZvDn9jyhYyo7OCho+pW8w5OLgQjiyD+Muw/SP451Oo1wceeE7tXzEVey1No9HQpLorTaq78mavelyITmJzqFrZ9NClGxy9fJOjl28yY+NpalV1oGeQWtm0WXXXcruu2dHLN5m76wJ/H79OTqG3el5OvNCpFv2b+pbaAtv3QmhsKN8e+ZadV3YCoNfoebzO47zY5EW8HXIDtr888gtxaXEAZGVlsWf3Htp3aI9er/7Ic7N1u61A2+2y0dlQzbEa1RyLf50ZjAZupN8wD8KlqdlyeaexxqTGkJqVSkpWChcTLnIx4WKx19Vr9LjbuRcIwhU2ndXqNtZSVBSFWUdm5WazVm8v69IJUclJ1pDlSPBSCCHuLxJsuwtGo5GFCxcyatQo04c4UD/Av/XWW3zwwQc0bdqUZs2asWjRIk6dOsXKlStN7bp168bjjz/OmDFjAEhKSuLcuXMoivoJ+XJSIqds7XAxGnCYMpXqs77hrbfeYvDgwXTq1ImuXbuyYcMG1q1bx44dOwr078cff6Rq1ar069cPgPbt2zNlyhT279/P33//TVBQEK6urvdugEpZRpaRFf+phRGGtanEWW2ZaXDl39xpoVf/A0O+9alcamRnrmVPDbXgOmkXEy4yestoYlJzF9dXUAiNDWXS7km89cBbVLGtUvjJHrWh13R46H0I/V3Ndru8H07+oW5ugdDqGbWaqX3pr11Sq6ojL3V25KXOgUQlprElVC2wsPdcLBeik5nzz3nm/HMeTycbegR50bOhNw/Wci/zAJbRqLD1VBTzdl3gQFicaX/HOh680LEWHet4VOigyJkbZ/juyHdsvbQVUKuH9gvsx0tNXqK6U/UC7b0dvE3Bt8zMTML0YTRwa4CVVfnK5tNpdabgVz2Kr1adnJlcaBAuJ4MuJi2GmJQYbqTfIEvJIjIlksiUyFv2wcXGpUAQLqcSa1X73O8drRzZe21vwWzW7LXvhBBC3JoEL4UQ4v4hwba7sGXLFi5dusSzzz5b4Njrr79OWloa48aNIy4ujqZNm7J582YCAwNNbc6fP09MTG7A4r///qNr166m259Fqh+UHnN25uPNm0n4+28ef/xx5syZwyeffMLYsWOpV68eq1atKlDlNDIykunTp7N3717TvtatW/PGG2/Qt29fPD09WbRokcXGojzYGBJBTFIGXs42dGvgVdbdsZysdDVbLSy7oMHlA2BIN2/j5JsdWMsOsLn6gYWDK4qisPbcWj4O/pg0Q1qhbdZdWMfG8I08WvtRhgcNp5ZLEdPtrGyh6WB1iwxRg25Hf4W487DpPdj6oZoJ1+pZqNHG4o+lJDydbBnapiZD29QkMS2THaej2RQayfZTUUQlprMs+BLLgi/hZKOna31Pejb0onPdqjjZll5AJy3TwKpDV5i/K4wLMckAWOk09Gvqy/MdahHk61xqfbkXLsRfYM6ROWwI34CCggYNfWr14ZWmr+DnXDCbtzJzsHLAwcUBfxf/YttlGjKJTYstEITLX/QhJjWGLGMW8enxxKfHc+7muWKva6O1wUjuWo/5174TQgghhBBC5NIoOWlU94mEhARcXFyIj4/H2bn8fRDNio3l/MO9MSYlQd7/Go0GrZMTgX+vR+8uZcELM2TuPvZfiGNstzqM71G3wPHMzEzWr19Pnz59yl2Gi5msDLh2GMJ3qgG2ywcgK9W8jaNXnsy1juoabPfwA298ejxT901l88XNt3Vex2odGdlwJG2829z6A3l6EpxYCf/Oh4hjufs9g9SgW5NBYOtyB723rPQsA/vOx7IpNJLNoZFEJ+YGPq11WtrVdqdXQ2+6N/CiqpPNbV27pM/R2KR0Fu+7yJL9F4lLVrManWz1DGvjx9Pt/Ct8YYfLCZf5/uj3/BX2F8bsYh49/XryarNXCXQNvMXZ5irM676UKYpCfHp8oUG4/MG5pMykIq8zp/scyW67S/IctSwZT8uTMbUsGU/LqyhjWt4/hwohLEsy28oRRVGImDIFY0qKeaBNPYgxOZmI7Omkwty5qET2X4hDq4GnWtco6+7cHkNWdnAtO3Pt0n7ITDFv41BVDar5d1CLGrjXLrVsr38j/mXirolEpkSiQ4eHvQdRKVFFVnr0d/bHz9mPf678w66ru9h1dRd1q9RlRNAI+gT0KXqtLBtHaPm0WjTh2iE12+34KogKhfVvwubJ0HigGnjzbX5vH3QxbPQ6utTzpEs9Tz56tBFHrtxkY0gEm0IiCYtJZsfpaHacjuZdzXFa1KxCr4Ze9Azyxv8WawgajArBYXEcjNHgHhZX6Dou56OTmL87jFUHr5CepQahqrna8VyHAAY9UANHm4r9ln4t6Ro/HPuB38/9jiG7qEfXGl0Z3Ww09dyKn2Ypbo9Go8HV1hVXW1fqVKlTbNuUzBSGrx/O+ZvnzbLbtBqtZLcJIYQQQghRiIr9yaySST97lsTNW4puYDCQuHkz6WfPYlOn+A9H95ul+9Uqr90aeOHjYlfGvbkFQxZEHM0taHBpH2Tkyxyxd1cDa/7ZmWtV65X6VMpMYybfHv6WBScWoKDg5+zHh+0+ZNyOccVWekzISODLLl9yPfk6y04uY+25tZy5cYb397zPzIMzGVJ/CIPqDcLNtog12TQaqNZS3XpOh2O/qoG36FNwaLG6+bZQg26NBoB12RXC0Go1tKhZhRY1qzDh4fqcj05iY0gkm0IiOHolnoMXb3Dw4g0+Xn+Kul6O9AzypldDbxpVczYLTmw4cT1PhTIdi8/+h092hbJeDb05EBbHvF1hbDmZuwZX0+ouvNCpFg839Eavq7hFDwAikyOZd3weq86uIsuYBUCHah0Y02wMDT0alnHvxOGow5y9ebbAfqNiJCQ2RNZuE0IIIYQQIh8JtpUjNnXq4NSjO4nbtkNhVUJ1OpweekgCbfmkZqjrVgEMb1sO13EyGiDieHbm2m64uBfSE8zb2FUBv/a5U0OrNijVqpz5XUy4yDs73yEkNgSAx2s/zoTWE7C3si9xpUc/Zz/ebfMuo5uNZuWZlSw/tZyolCi+PfItPx7/kX6B/RjRYAS1XItY1w3AzhXavAStX1SDkv8tUAsrXDsEfxyCjZOg6RC1qIJng3s9LMXSaDTU9nSitqcTo7vW5np8KltCI9kYEsn+C7GciUziTOQ5Zm8/h4+LLT2zCyzcSMng/5YfLhC+jIhP4+Wlh/Bzt+dibG6mY/cGXrzQMYDWAW4VPpsoJjWG+cfns+L0CjKM6nTYNj5tGNNsDM08m5Vt5wSQXYH08Cw0aIrMZpXsNlHmtn8CWh10frvgsX8+V38Od51Y+v0SQgghxH1Lgm3liEajwXvKFJL3Bxe+ZpuDA95TPii7DpZT645eIzEti5pu9nSs7VHW3QGjEaJCcjPXLu6GtHjzNjYu4N8+d2qoV6MyDa7lyCmC8MmBT0jNSsXZ2pkPHvyAnv49TW1ut9Kji40LzzV+jpENR7IpfBOLQxcTGhvKyjMrWXlmJR2qdWBE0Age9Hmw6A/rGg34tVO3hz+FI8vgv4VwIwwO/KBuNdup2W5B/UF/e2ul3Qs+LnaMeNCfEQ/6E5+SyfbTUWwMieCfM9Fcj09j0b6LLNp3EQ0UmieYs+9ibArWOg0DW9XguQ4BBFZ1LMVHcW/cSLvBwpCF/HLqF1Kz1yNs4dmCMc3H8ID3A2XcO5FXpjGTiOSIYrNZI5IjyDRmFj1FXIh7TauD7dPV79uNy93/z+fq/q6TyqZfQgghhLhvSbCtnNG7u+MzdQpXx79hfkBR8Jk6RYojFGJZ8EUAhrapibYsSqgbjeoUx/BdELYTLu6B1Bvmbayd1EBRTkED78bqh4NyJH8RhAe8H+DjDh+bAmt3y0prRd9afekT0IdDUYdYHLKY7Ze3s/vqbnZf3U2dKnUY0WAEfWv1Lf5Du4MHtH8NHvw/uLBdzXY7/Tdc2qtuG9yh2TB1/Tf321tM/15xsbfisebVeKx5NdIyDew5F8OmkEj+PnGdhLSsW54/66nm9GrkUwo9vbfi0+NZFLKIZSeXkZKlZus19mjMmGZjeNC3mGCrKDPWOusSZ7MKUWZyMtq2T0drMABBaHd9ATs/VQNthWW8CSGEEELcQxJsK4ecevfG6e+/c6eTZk8fde7du6y7Vu4cvxLP0SvxWOu0PNmyeuncqaJA9OncggbhuyEl1ryNlQP4PZg7LdS7KejK78stbxEEvUbP6OajeabhM+juQUBQo9HQ0qslLb1acinhEstOLmPNuTWcvXGWyXsn879D/2Nw/cEMrje46HXdQM0ErN1N3RKuwaElcGgRJFyFvd+oW+BDarZb3YdBVz6qU9la6ejWwItuDbxoG+jOuF+P3PKctCzjLduUZ0kZSSw9uZTFIYtJzEwEoIFbA0Y3G02n6p0kyFbO3W42qxClLiUOaraF2t3R7fyU/tkTn2k2FNr9X1n3TgghhBD3ofL76f8+lnc6qSExEZ2DvUwfLUJOVlvvxt64O96jqYOKArHnsjPXsoNryVHmbazsoUab7My1TuDbrNwEd4pTWBGETzt+SiOPRqVy/zWdazKxzURebfYqq8+uZtnJZUSmRPLdke/48Vj2um5BIwh0vUWGmrMvdHkHOr4BZzep2W7ntsD5berm5AMtRqqbSykFZUvA29m2RO08nUrWrrxJyUzh51M/szBkIfHp6lTq2q61GdNsDA/VfEiCbEKI26MocCMcIk+oa6HmbPGXzZppcqY9H1muVrWu0Tr7j1+d1OI7esnEFEIIIcS9JcG2ckrv7k7VyZO5OnUqPpM/kOmjhUhIy+T3I9cAGNbGgoURFAXiLqhBtZzMtcTr5m30tmpwLSdzzbdFhfvlvbgiCKXNxcaFZxo9w/Cg4WwO38zi0MWExIaw6uwqVp1dRftq7RkZNLL4dd1AzR6s30fdboTDwUVweIn6//fPZ7Bzhprl1upZNeutjKfytg5ww8fFloj4tEJXxNIA3i62tA4oJsOvHErLSmPF6RXMPzHfNP3Q39mfV5u9Si//Xmg1Zb8+oRCinMtMU5doyBtUizxRsMBQDtea6s/mmDMY0aLFCNaOarXvnEz0HR+rfxyr2Tb753dn8CnfmedCCCGEqJjkt4tyzOnhXlwwGqjfq+etG9+H1hy6SmqmgbpejjzgX6XwRiWtUHYjPDdrLXyXOhUxL51N9l/GO6i/oFdvVS4W4b8TJSmCUFastFb0qdWH3gG9ORx1mMWhi9l2aRt7ru5hz9U91HatzcigkfSp1Qcb3S3Gv4o/dP8AukyEU3+q2W7hu+D0enVzramu69Z8BDh6lsbDK0Cn1fBBvyBeWXqoQKGEnJDiB/2C0JXFWoR3IMOQwaqzq/jx2I9EparZn9Udq/NKs1foE9AHvVZ+5AghCpEcC5HHzQNrMWfAWMiallortfq0dxPwbqSugerVCA7Mhe3TMXSawJ+JQTziFIpu56fQ5mXwqJP9M36XuuxDTtYzgI2zuqZqTuZbOSlYJIQQQoiKTT75iApJURSW7lenkA5r41d0tlNRFco2ToJ9s9Vf0o8sh/hL+c6zguoPZE8L7aB+b2V3Dx5J6brXRRAsRaPR0MKrBS28WnA54TLLTi1j9dnVnLt5jsl7JzPz0EyG1BvCoHqDcLe7Rdan3hoaDVC36DNwcKFazfTmJdg6TQ3INnhEzXbz76hWPi1FDzfy4fvhLZi6LpTr8Wmm/d4utnzQL4iHK0BhhExjJr+f+50fjv1ARHIEAD4OPrzU5CX61+6PlbaUp1SXNMguhChdRqNaRTp/tlr+P3DlsHUFnybg1Vj9ee3dGDzqFswkz1N11NhuHKxfj7Hjm+h0utxqpIMWZRc0OqkG3sJ25lYLP7NB3QDsqoBfezXrLaAjVK1f6j8XhBBCCFHxSbBNVEj/ht/gbFQSdlY6Hm9RreiGeSuUxV6g2ZWr6L8cC2k31f0Rx9WvWr26jot/dnCtRhuwLv3plPdSaRZBsKQazjWY0HqCuq7bmdUsO7WMiOQIvjv6HT8e/5FHAh9hRIMR1K5S+9YXq1oXHv4Euk2GkDVqttuVf9XvQ9aAex1o9Qw0fQrsS2/q5sONfOgR5M2+c1Fs2hVMz45teLC2Z7nPaMsyZvHXhb+Yc3QOV5KuAOBp58kLTV5gQJ0BZVehsqgge54P5EKIeywzFaJC8wTWTqiBtYykwttXCcjOVGuSG1hzrlayQJfRkFt1NDMzd3/O7wBGg/pVqwWvhurW9mV1f8Sx3ODbpX1qNfFTf6obgIOn+ntBQCd1c6slwTchhBBC3JIE20SFlJPV9lhzX5xtb5E10/51OLcF3bGfyV3ZTaMG1wI6qgG2Gm3AxvEe9rjslHURBEtxtnbm6UZPMyxoGFsubmFxyGJOxJ5g9dnVrD67mva+7RkRNIJ2vu1uvfC+lZ1apa7ZULh+TM12O7YCYs/CxnfVjLeGA9Rst+qtSuWDlU6roU2AG7EnFdoEuJXrQJtRMbIhbAPfH/2e8IRwANxs3Xi+8fM8WfdJbPVlXNCh89uQla4G2aNOYa+0Q7vrC9j5ae4HciGE5SRFq0GrvIULYs6AUkglZZ1N9jTQxrmBNa+GYOt85/dfXKZqca93rQ58m6tb+7FgyIRrh9XAW/guuLRfLYgUslrdQA0A5kw5DeioLkkghBBCCJGPBNtEhROTlM7fJ9SCBbcsjHDjIqx8Fq7+Z9qlaPVo3g67u1/sK4jyVATBUqy0VvQO6M3D/g9zJPoIi0MWs+3yNvZc28Oea+q6biOCRtC3Vt9br+sG6hSlR76GHtPg+G/w7wJ17aCjy9XNq7Ga7dZkENg43fsHWI4ZFSNbL23luyPfce7mOQBcbVx5ptEzDKk3pPSfV2nxajET0xaW+31SJAC6kFX0YJXavkF/eHBM6fZRiMrEaFBfXxH51ldLiii8vb17bpZaTmDNvU75LUigs1LXZ63RGjq9qQbtr/yXG3y7fECd8nrsF3UDdX3QnOCbf0dwLv9T/4UQQghx75XT33aEKNpv/10h06DQtIYrjaq5FN3w5J/w+6vqB3K9DWSlY9Do0RmzIHhOpc5uKc9FECxFo9HQ3LM5zT2bcznxMstPLjet6/bB3g/436H/MbjeYAbVG4SHncetL2jjpGaytXxG/XD13wI1kyHyOPw1HjZPhsZPqm18mtz7B1iOKIrCP1f+4dsj33Iq7hQATtZOjAoaxfCg4ThYOdyrO1andJkF1PJsKbHFn2/nhpJ6A01O6YmTf8D57er6fc2Hq2sxynQwIQqXkZI9DfRYnvXVQiAzpZDGGnV6Zf7AmpN3xX6N6W3Av726MVEdk8vBauAtbCdcPaQWWLoRrla+BjWYmJP15t8RHErw80cIIYQQlY4E20SFYjQqLD+QUxihiKkbWelqYCR4jnrbyRcSr5lXKMtZz6kSBtwqShEES6rhVIN3Wr+jrut2djVLTy4lIjmC749+z/zj8+lbqy8jgkZQp0qdW19Mo4EaD6hbr+lw9Bc18BZ7Vp1uenAhVGulBt0aPl7p1vbLS1EU9l7by7dHvuV4jLq+oYOVA8MbDGdkw5E4W1sgO1RRICnKPIh2I0+GWlp88ec7eqkf8t1qgVtA7vdVAuDAXDTbp2PU6NAqBnWx9bSbcGiRunnUhWbDoOkQNSggxP0qMTI7oJYnsBZ3vvBpoHpbddpnTmDNqzF4Bd0fmb/W9hDYVd0A0hPh4j4I36kG364fU39WxJ6F/+arbTwb5gbf/NqDnWuZdV8IIYQQpUeCbaJC2Xk2mstxqTjb6unXxLdgg7gw+O1puH5EvV2jjfpX6KIqlEGlCrhV1CIIluJk7cSohqMY1iB7XbfQxRyPOc6ac2tYc24N7XzbMSJoBO192996XTdQiyQ8+Cq0fQXCd6tBt5Pr1GnJV/+DjRPVYE3LZ9TiC5XIgesHmH1kNoejDgNgp7fjqfpP8UzDZ3C1db29ixmNkHi9kOy07KBaZnLx5ztXKxhMywmoFbXWYnYxBLMg+85P1Yw2oxFC16prSm35QF2jr04P9VidXgUrHQpRWRgNEHsuX2DthLouWWEcqmZnqeUpXOAWWH6ngZY2Gyeo21PdQM3EDd+Tnfm2C6JCcrfg7wEN+DRVA28BnaFm2/sjSCmEEELch+S3JVGhLAu+BMATLatjZ50vgBSyFv74P0hPALsq8Nj3cO0I1O5+6wplFVxlKYJgKXqtnocDHqaXfy+ORh9lcehitl7ayt5re9l7bS+BLoEMDxrOI7UeKdli/hpN9oejjmoW1uGlaobbzUuw/zt18++oru1Wv1+FDtYcjjrM7MOzORBxAAAbnQ2D6g3i2UbPFj8d12iA+Mvm66blfH8jDLLSij5XowWXGkVkqPmrBS1uR56qo4UG2btOgjfPqBVoDy+Dy/vhzAZ1s3eHJkOg+TA1e0eIiio9SZ32mbdwQWQoZKUW0lgDHnXAq1G+aaBepd7tCs2uCjR4RN0AkmNyp5yG7VIz3q4fUbe9s0Cjyy3WFNBJ/QPh7b7fCSGEEKJckmCbqDCu3Uxl60l10XOzwgiZabBpEvz7o3q7RhsYuABcqkO93kVfsJJktOUvgjCgzgDeeeCdCl0EwVI0Gg3NPJvRzLMZVxKvsOzkMlafXc35+PNM3TeVbw59w+D6gxlcb3DJ1nUDcPSEjuPVKrfnt6lThc5sUD9Qhe9SM0GaD4eWT6uBogriRMwJZh+ezZ5rewA1YDmwzkBeaPICnvaeaiNDphpgLGz9tBsXwZhZ9B1o9eDqZ56ZlrO51rRsgNJoyK06WlSQ3cYJWoxUt5izcGQZHPlZXeh9/7fq5tNM/b9sPFD9EC1EeaQoauZo/qIFcRcgZ73CvKzszaeBejdRq4Na36O1F+9nDh7qcgMNH1dvJ1zPE3zbCTcvwpUD6rbrS9BZQ/XWucG3aq0q9B9vhBBCiPuZBNtEhfHLgUsYFWhby43antlTx2LPw2+j1A8WoAZAHnpPrShWyRVWBGFKuyn08OtR1l0rl6o7VTdb123ZyWVcT77OnKNzzNZ1q1ulhNNBtVqo013d4q/AocVwcJEarNn9NeyeCbW7qWu71elVbqddnYo7xbeHv2XHlR0A6DU6Hq3elZc8HsAn+QZs/yw3oHbzMijFZIPqrNWpnYVlqLnUKL0x6Dqx6GOFBdk96kD3KdD1PTWAengJnP47NwNl4yQ1U6XZMKjVBe6TadniHtr+ifo8Kuz5+M/n2QHjQp7Hhix1+nPkCfP11YoqFuLonSeolh1YcwuQ53BZcfZRK1s3GaTevnExd8pp2E5IvAYXd6vbjk9Abwc122RXOu0Evs3L7c8SIYQQQpiTn9iiQsg0GPnl38sADG+bndV2fCWsew0yktSpX4//oK67dB+4H4sgWEredd22XtrK4tDFHIs+xtpza1l7bi0P+jyorutWrT1ajbZkF3WpDl3fhU5vqVlu/y1QgzbntqibczVoMQpajADnQtYaLG0ZyZy7tJPvQhex+YaaEakFHklXeDnqMjUuLAAWFH6ulX3u9M78GWrOvhX7Q7xOn7v+UnIsHF+hThmOPAEnVqmbczVoNlTd3GqVdY9FRaXNs25ou3G5+/NMgSYtIXsaaJ711aJOgiG94PU0WrXgR97AmldjcKxaOo9H3JkqfurWfLiaoRh3AcL+UYNv4bsgORou7FA3AGsn8HswO/jWUf1/rsjvuUIIIUQlJsE2USFsCY0kKjEdD0cbetZxUYNsB39SD9ZsBwPnl48gRim434sgWIpeq6eXfy96+ffiSNQRloQuYculLey7vo991/dRy6UWI4JGlHxdN1AzKhv0U7fY82rFy8NLIeEq7PgY/vlMndrc6lmo1VXNjrtX0uILXT8tPP4C31lnssHBHkWjQaMoPJycwis34wnIzFLPtXYC90Kme7rVUqt/lqS4REXn4K4WxmjzMlw/qk4zPbZC/b/cOUPd/Dqoa7sFPSpT8MTtyclo2z4drcGAbYYX2rUvQcgq8KinPt9ygnH5WTvmWVste/NsIGt9VXQaDbgHqlurZ9XgW/Sp7Ky3f9QiPWk34ewmdQO1wrJ/h9zgm2eD++P9WQghhKgAJNgmKoScwgivNMrCemEPtbIXGuj0JnSecF9Mq5AiCPdOzrpuV5OumtZ1uxB/wbSu26B6gxhSf0jJ13UD9QNTj2lqhsrJdWq228U9cOpPdavir1YxTYlV1w+73elkAClx+QJqebaUGLOml/U65ri68GcVB4wadQ2gHkZrXnGoRx2/RuYBNXt3+cCWQ6MB32bq1uNDOL1eDYSc25o73Wv9W+qaTM2Hq2tGytiJW4m/Ak4+4BmEbuen9Mp7LOZ07vfO1bKz1PIE16oE3NtAvSgfNBo1eObZANq8qFZRjjyem/UWvkcNvuX8TAGw91DXe/PPrnbqHijvR0IIIUQZqfwRClHhhcUks/tcDAN0u3gmZBFkpqiL0A+YC4EPlXX3SoUUQSgd1Ryr8fYDb/Nq09x13a4lX+OHYz+w4MQC+gT0YUTQCOq51Sv5RfU26gL7jQeqU8D+WwhHf4Eb4bDlA7UanWJQF8ru/XXueTnTydq/Bpf2Fx5QS4sv/r4dPLnuVpMf7DT8nhlFVvZi6V182vFqy9dp4N7g9gfpfmZlC40GqFv8VTj6sxp4i7ugrvN2eAm411bXdmv6lLo+kxCgTgkN3w0XtsP57WpVynwUNGiaDDKfBurgXgadFeWSVgs+TdWt3Rh1/b7rR7Oz3nbBxX3qH1lC1qgbqAHdnKy3gE7qlFUhhBBClAoJtolyb8Xe03yu/4FB+n8gE/WXxid+BKfKvz6ZFEEoG47WjoxsOJKhDYay7dI2Focu5mj0UX4//zu/n/+dtj5tGRE0gg7VOpR8XTdQMxT6fA7dP4ATq9Vst2uH1GOHl6I//TcNHVqh+2G6mt2is4Y9/1O3ojj5FixG4FaLKDtH5p36mVVnV5GZXZGzvW97RjcbTeOqje9idAQALtXUzNqOb8ClfXB4mfoBN/YcbJ0K2z6E2t3VbLe6vaWi4P3GkKW+ts9vVwNsV/4FY1bucY0WfFuowfiLezBo9OiULDVY2+7/yq7fouLQ6aF6S3XrOB6yMuDqwdxqp5cPqFVqj/2qbqBWfvbvpAbeAjreN8tvCCGEEGVBgm2iXEu/FsLAQyMI1F9R/+rfZYK6CP19sD6ZFEEoe3qtnp7+Penp35Oj0UdZErqEzRc3s//6fvZf30+ASwAjgkbQr1a/kq/rBur6Xi1GqNu1w2q225HlaFJiqZ2yMbedIQPQqJU88wXTTEUKrM2zG2NTY5l/Yj4rTq8gPXsh9dberRndbDQtvFrc/aAIcxoN+LVTt96fQehadZ2+S/ty11ayc4Mmg9X13bwl0Fkp5Sxuf36buph92C5Iz5d5WiUAAruq6zUGdIQD82D7dAydJvBnYhCPOIWiy1mnrbBp5UIUR2+tFk/we1B9/mSmqgG3nODb1YNw8xIcWapuoAZ3c7Le/DuaF9S404q5QgghhAAk2CbKK0WBI8vQ/fkGgaQRQxWqjFiELrBzWfesVOQvgjCm+Riebvi0FEEoQ02rNqVp56ZcS7rG8pPLWXV2FWHxYUzbN820rttT9Z+6vXXdAHybQ//m0PNDlM8C0CgGFI0OzZDl2QE1PzX75RZupt1kYchCfj71M6lZqQA092zOmGZjaO3T+k4esrhdNo5qJlvz4RBzTp1ievRnNbsk+Ht182kKzYar04rt3cq6x+JupMRlV4rcDud3QPwl8+O2rmoQI/AhNchWxT/3WJ6qo8Z242D9eowd30Sny1OlVAJu4m5Y2UGtzuoGkJ6kLkkQvlMNBl8/ombixp6DgwvVNp5BucE3Qwb885W6v6iKuUIIIYQokgTbRPmTngR/vQHHfkEP7DQ05mz7L3gusG1Z9+yekyII5Z+voy9vPvAmLzd9mTXn1rDs5DKuJl1l7rG5pnXdRgaNvL113QCCf0CjGHKnk0Ucg3oP3/K0hIwEloQuYUnoEpIzkwFo5N6IMc3H0M63HRpZHLtseNRWpws/9J6a7XR4qVpc4fpRdds0Cer3VQNvgV3vi2zdCi8rXQ1W5Ky7dv0oZK+DCIDWSi2QEdgFaj2kFtUo6v/VaFCDFZ3fhuxp3kBugM1ouEcPQty3bByhTnd1A0i9qWbghmUH3yKPQ1Souh34AdCAo7daMTfqNNaaLmh3fQE7P8197gohhBCiSBJsE+VLZAj89jTEnEHRaPkiYyBzlUfZ075ZWffsnpMiCBWLo7UjI4JG8FT9p9h+eTuLQxZzJPoIf5z/gz/O/0Eb7zaMbDiyZOu6ZWcK3M50suTMZJadXMZPIT+RmJEIQH23+oxuNprO1TtLkK280OqgTg91S4mD47+pgbeIY7kLmTv5QrOn1MIK7oFl3WORQ1HUn0k5wbWLeyE7a9SkaoPcqaF+7dSARkkUN/1OghiiNNi5Qr3e6gaQHKtWVw7LnnYacxqSIgDQhaykNyvVdvbu6vTUP8era8C51gRXP/Wrg4dUPxWlR6Y6CyHKOQm2ifJBUeDQIvj7HchKAycffvScxLchbvRt7IOn022sh1XBSBGEik2v1dPDrwc9/HpwLPqYaV234IhggiOC8Xf2V9d1C+yHnd6u4AVuczpZSmYKv57+lQUnFnAz/SYAtV1r82qzV+lWs9vtFWwQpcveDdq8pG7Xj6nTTI/9ConXYNeX6laznbq2W9BjJQ/cCMtJuJ4bXLuwA5KjzI87ekGtLmpwrVYXqTgrKg8Hdwh6VN0AEiPUCrphO1EOLcIUQkuJhXObC7+G3i5PAK6mBOPEvaXN83uSTHUWQpRDEmwTZS89Eda9Diey/2pauztJfb9l5tdHAAPD2tYsw87dW1IEoXJpUrUJMzrP4HrSdZafWs7KMysJTwjnw/0f8s3hbxhUV13Xrap9nkWoSzidLN2QzorTK5h/fD6xabEA+Dn78UrTV3jY/2FZz6+i8Wmibj2mwem/1Wy381vh0l51W/82NHxcXf+tZlv5gHqvZCRD+J7cAFv0SfPjejvwb68G1wK7qmtayf+FuB84eatrS8ZdQAO5Sxw0fQpqPqgWW8i7JV5XMz9jTqtbYazsiwjGZQfk7N3l9SVuTVEg9QY06A83wmD7dHQX99Eg2QHtrlCZ6iyEKDck2CbK1vVj6rTRuPOg0UG396Hda6w9cJnkDAO1qjrwYC33su7lPSFFECovH0cf3mj1hrqu29k1LD25lKtJV5l3fB4LQxbSJ6API4JGUN+tvtkUh+CIYP6X8D/cI9zpUKMDdH6bTEMmq0/9ytzjc4lKUbNsqjlW45Wmr9C3Vl/0Wnkbr9D0NtDwMXVLuKYWVDi8TH1PzKka6BaoZrs1fQqcfcu6xxWb0QDXjsCFbWpRg8vBYMwT5EajrrWWE1yr0aZEBUqEqJQKW+Jg56dq8Z5u75u3zUqH+CsFg3B5g3GZKRB9St0KI8G4+1tGMiRFZW+R2VtU4V/N3rdBe2EbdQEi10mgTQhRbsinNFE2FAX+mw8b3gVDOjhXg4ELoGZbFEVhWbBa1W1YG79Kt/ZUYUUQPuv4GQ09GpZ114SFOVg5MDxouGldtyWhSzgUdci0rltr79aMDBpJx+od0aBh1pFZRBujmXVkFq19W/PnhT/54egPXEu+BoC3gzcvNXmJR2s/ipXWqowfnbA4Z1/o+AZ0GK8uxH9kKYSsVQNvW6fBto/UypbNh0O9PhIEKqm4sNzMtbCdkHbT/LhrzdzgWkBnqRIrBNx+xVy9jbrmZFHrTkow7v5kyITk6HwBsyKCaBlJt3dtW1d1ar+jJ8rFPWgUI4rOGo0E2oQQ5YQE20TpS4uHP8ZC6Fr1dt2H4bHvTR9wDl26ycnrCdjotQxsUb3s+nkPSBGE+5NOq6O7X3e6+3XnePRxloQuYdPFTRyIOMCBiAP4O/vzoM+DhMaFAhAaF0qvVb2ISY0BoKpdVV5o8gJP1HkCa511WT4UURo0GvB7UN0e/gxCf1fXd7u4B85tUTe7KtB4kJrx5tO0rHtcvqTeUINq57erQbYb4ebHbZwhoFNuYQO3WvIBXYj8LF0xV4JxlUfONM4CgbNCgmgpsbd3bb0dOHmZgmg4eoGDZ+73pv2euX9w+udzNOG71KnOhgw1UCwBNyFEOSDBNlG6rh1Wp43eCAetHrpPhQdHm/3ysyz4IgD9mvriYl85snekCILI0bhqYz7v/Dnjksbx86mfTeu6hSeEm7WLSY2hik0Vnmv8HIPrDcZWX3mLhIhi2DiqAbXmwyD2PBxZrm6J1+DAD+rm3RiaDYcmg+7PrKysDLjyL5zfpgbXrh0GxZh7XKuH6g/kZq/5tgCd/PojRLFKu2LubQfjLlooGOeXJxjndn8H49KTisg6i8yXnRZVYBpnsTS63ABZ3iBaYd9bO97e/8EdVHMXQojSIr9titKhKHBgLmx6DwwZ4FITnlwI1VuZNbuRnMGfx64DMLytX1n01OKkCIIojI+jD+Nbjeelpi/x1X9fseLMigJtpjw4hYf8HiqD3olyyT1QXSep67tqUOnwUjj1F0Qchw3vqO+v9ftA8xHqdNPKuv6jokD06dypoeG7ITPZvI1H3dzgmn8HsHEqm74KISyjxMG4i3eRGedwi8y4uwjGbf9EfU8uLAD0z+fZmYTFBDjvVFZGIdM4i8hEy/8+eit2VYoJnuXZZ+cG2ntQKf12pzoLIUQpk2CbuPdSb8DvY+DUn+rt+o/Ao7PVH9L5rDx4hYwsIw19nWla3aWUO2p5UgRB3Iq93p6Q2BC0Gi3GPNk4Wo2Wucfn0rVm10q3bqG4S1od1O6ubilxcGIVHF4C14+qU05DfwcnH2g6RM1486hd1j2+e0lRcGFH7tTQxOvmx+09oFaX3KmhLtXKopdCiLJyq2BcZhokXL1FMC5ZrUicvypxjrsJxmnzBIDajcvdnydgVGJGI6TGmWeaFTWNMzWu5NcFNfuvqKyzvFM4HaqW/bqhlp7qLIQQFibBNnFvXTkIK59Wf5HRWkHPj6DNS4X+MmI0Kiw/oBZGGN62YhdGkCIIoqT2XttrWsMvL6NiJCQ2hL3X9tK+Wvsy6JmoEOzdoPUL6hZxXK1keuxX9YPj7q/VrUZbdRpqw8crToZXRgpc2psdXNsBkSfMj+ttoeaDucE1r0b3JnNCCFE5WNmWbTCu1XNqVu726WgNBiAI7a4vYOenasCo01uQnlhE4Cx/EC0KlNsIJGn1+dY9KyYTzcbxtoe2zJT2VGchhLhNEmwT94aiwL5vYcsHYMyCKv4wcCFUa1HkKXvPxxIWk4yjjZ7+TX1Lr68WJkUQREkpisKsw7PQoEFBKXBcg4ZZh2fRzrddhQ4+i1Li3Rh6fwo9psGZv9XA27nNcHm/uv39DgQ9plYz9WtXvtYmMhoh4mhu5tql/eqSA3l5N8kNrtVsC1Z2ZdNXIUTlc7vBuBv5gnJJESULxtl7oNv5Kf2zf/LjXF0tgLP7a3Wa6+2wdy9BEM1LnUkif4wQQohSJ8E2YXkpcbD2VfXDHkDQo9B/FtgWPy00pzDCgBbVcLCpeE9NKYIgblemMZOI5IhCA20ACgoRyRFkGjOlCqkoOb21+r4b9CgkXIdjv6iBt9izcHS5ulUJULPdmj4FLmVU9fnmpdzg2oV/Ck53cq4OgV3U4FqtLuDgURa9FEKIkgXjilszLicYl70umibn537CFfPrWDsWEjwrJIjmUBV0laOImBBCVFYVL6IhyrdLwbDyWfWXB5019PoYHnj+lhkUkQlpbAqNBGBYm4pXGCF/EYTW3q2Z3mG6FEEQxbLWWfPLI78Ql6YGGbKystizew/tO7RHr1ffnt1s3STQJu6csw90GAftX4fLB+DIUjixGm6EwbaPYNt0NVus+XCo11f9QHmvpMWrxQzOb1ODbHHnzY9bO0FAx9zCBu61y1f2nRBCFMXKVl0fs6g1MnOCcTtnwLFfMKJFixEaDlCXV3H0VLPUKtI0TiGEEMWSYJuwDKMR9n4DW6ep60i41YInfwKfpiU6/dd/L2MwKjzgX4V63hVkTaFsUgRB3A1vB29TUDYzM5MwfRgN3BpgZSV/sRYWpNFAzTbq9vCnEPqHWs30Yk7waxvYukLjJ9WMN59mdx/oMmTC1YO52WtX/jNfZ0ijg2otc6eGVm8lmRpCiMrJyhZCVsOxXzB0msCfiUE84hSKbuen4NlA1hgTQohKSIJt4u4lx8Kal9S1gQAaPQGPzARb5xKdnmUw8nN2YYSKlNUmRRCEEBWStQM0e0rd4i7AkZ/hyHI1I/nfeerm1QiaDYMmg+DAPLWSXmEfBv/5PLsi3ER1rc7Yc7nBtbBdkJFo3t4tMDe4FtDxlssLCCFEpZCn6qix3ThYvx5jxzfR6fJUKZWAmxBCVCoSbBN35+JeWPkcJF5Tq8M9/Cm0fPq2MiK2n47menwabg7W9G5cMaZdShEEIUSl4FYLHpoEXSZA2D9qttvJP9XqnxsnwubJapuY02oGc4c3cs/N+fAY9Bj8PhrO7yi4/pCdG9TqnDs11LVmaT46IYQoH4wGtepo57chMzN3f06AzXgb1UWFEEJUCBJsE3fGaITdX8H2j9VpQe511Gmj3o1u+1JL96uFEZ5sWR0bffmeeilFEIQQlZJWB4EPqVvqDTi+Uq2Qd+2wGmgD+OcTdBe24WXVDt3ib+FysLo/dG3udXTWaqXQnOCad1OpgieEEF0nFn1MMtqEEKJSkmCbuH1J0bD6BXWaEECTwdD3qzta1PVSbAo7z0YDMLRN+c54kCIIQoj7gl0VaP2CukWGqJVMj/0KKTFoLwfTlmDz9l6N1GqhgV2hZjuwlgxfIYQQQghxf5Ngm7g9Ybtg1fNqCXO9HfSZoVaxu8OFtJcfuISiQMc6Hvi5O1i4s5YjRRCEEPclr4bw8MfQfQqc3YiyYgQaRUHRaNE8/gMEdAYnr7LupRBCCCGEEOWKBNtEyRgNsPML+OdTUIxQtb46bdSzwR1fMj3LwG//XQZgeNvyWRhBiiAIIQSgt4aok2gUBYNGj07JghvhagEFIYQQQgghhBkJtolbS4yE1c9D2E71drPh0OdztaLdXdhwIoLY5Ay8nW3pVt/TAh21LCmCIIQQ2bKLIRg6TeDPxCAecQpFJxX0hBBCCCGEKFS5WLX422+/xd/fH1tbW9q0acOBAweKbNulSxc0Gk2BrW/fvqXY4/vI+e0wp70aaLOyh8d/gMe+vetAG8Cy4EsADGldA72uXDwVAbUIwpqza3hy3ZOExIbgbO3MV12+Ymq7qRJoE0Lcf3KqjnadhLHjmwDq166T1P3/fF7GHRRCCCGEEKJ8KfPMtl9//ZXx48czZ84c2rRpw8yZM+nVqxenT5/G07NgttPq1avJyMgw3Y6NjaVp06Y8+eSTpdntys+QpU4Z3fkFoIBnEDy5CKrWtcjlz0QmciAsDp1Ww5AHyk9hBCmCIIQQ+RgNamCt89uQmZm7PyejzWgom34JIYQQQghRTpV5sO2rr77ihRde4JlnngFgzpw5/PXXXyxYsIAJEyYUaO/m5mZ2+5dffsHe3l6CbZaUcB1WPQcX96i3W4yC3p+BlZ3F7mJ5dlZb9waeeLvYWuy6d0OKIAghRCG6Tiz6mEwhFUIIIYQQooAyDbZlZGRw8OBBJk7M/UVeq9XSvXt39u3bV6JrzJ8/nyFDhuDgUPi0xvT0dNLT0023ExISAMjMzCQz71/oy6Gc/pVmPzXnt6L741U0KbEo1g4Y+nyF0vCJnA5Z5D5SMrJYefAKAENaVS+1x1fUeGYaM5lzbA4/hf6EgkJNp5p83O5jgtyDMBqMGA3GUulfRVQWz9HKTMbT8mRMLUvG0/JkTC1LxtPyZEwtS8bT8irKmJb3/gkhLEujKIpSVnd+7do1qlWrxt69e3nwwQdN+99++23++ecfgoODiz3/wIEDtGnThuDgYFq3bl1omylTpjB16tQC+5cvX469vay/lUOjGKh/fRV1I/8EIN6uJv/6jybZ1sfi97UvUsMvF3R42ChMam5Aq7H4XZRYjCGG31J+46rhKgAtrVvSx64PNhqbsuuUEEIIIYQQolJJSUlh6NChxMfH4+zsXNbdEULcY2U+jfRuzJ8/n8aNGxcZaAOYOHEi48ePN91OSEigRo0a9OzZs9y/yWVmZrJ582Z69OiBlZXVvbujhKvo1ryINlINbhpaPIN9jw/prL830zvnfb8fSOC5LvV4pIP/PbmPwuy5sodpu6cxucNk2lVrx+8XfueHgz+QakjF2dqZ91u/T7ea3UqtP5VBqT1H7xMynpYnY2pZMp6WJ2NqWTKelidjalkynpZXUcY0Z4aVEOL+UKbBNg8PD3Q6HZGRkWb7IyMj8fYufkH65ORkfvnlF6ZNm1ZsOxsbG2xsCmYpWVlZles347zuaV/PbIQ1L0HqDbB2gv7foGs0gHu1StnRyzc5cS0Ba72Wwa39Su3/QFEUvj/xPdHGaGYfn83v4b+z5dIWQIogWEJFej1VBDKelidjalkynpYnY2pZMp6WJ2NqWTKellfex7Q8900IYXnasrxza2trWrZsydatW037jEYjW7duNZtWWpjffvuN9PR0hg8ffq+7WTkZMmHTe7B8kBpo82kGL++ERgPu6d0uC74IQN/GPrg5WN/T+8pr77W9hMaFAnD6xmm2XNqCXqPn9RavM7fHXAm0CSGEEEIIIYQQwiLKfBrp+PHjGTVqFK1ataJ169bMnDmT5ORkU3XSkSNHUq1aNT755BOz8+bPn89jjz2Gu7t7WXS7Yrt5CX57Bq7+p95u/RL0/BD093adsviUTP44eg2AYW1q3tP7yktRFGYdnoUGDQrqEoXWWmsWPbyIRlUblVo/hBBCCCGEEEIIUfmVebBt8ODBREdHM3nyZCIiImjWrBkbNmzAy8sLgEuXLqHVmifgnT59mt27d7Np06ay6HLFduovWPsKpMWDjQs8OhuC+pfKXa8+fIW0TCP1vZ1o6VelVO4T1Ky2kNgQs30ZxgziM+JLrQ9CCCGEEEIIIYS4P5R5sA1gzJgxjBkzptBjO3bsKLCvXr16lGER1YopKwM2T4bg79Xbvi3gyYVQxb9U7l5RFJYFXwLUrDaNpnRKkBaW1Qag1WiZdXgW7XzblVpfhBBCCCGEEEIIUfmV6ZptopTcCIcFvXIDbQ+OgWc3llqgDSA4LI5zUUnYW+t4rHm1UrvfnKy2vIE2AKNiJCQ2hL3X9pZaX4QQQgghhBBCCFH5SbCtsgv9HeZ0gmuHwNYVnvoFek0HfekVJwBYul8tjPBos2o42ZZeBdKcrLbCaNAw6/AsyZIUQgghhBBCCCGExZSLaaTiHshMU6uN/jtPvV29NQxcAK41Sr0r0YnpbAyJAEq3MEKmMZOI5IgCWW05FBQikiPINGZirSvd4KMQQgghhBBCCCEqJwm2VUax5+G3pyHimHq7/Wvw0PugK52MsvxW/HeZTINCsxquNKrmUmr3a62z5pdHfmHesXmsOLOCVp6taJ3SmvYd2qPXq099N1s3CbQJIYQQQgghhBDCYiTYVtmcWAV/vAYZiWDnBo//AHV7lll3DEaFnw+ohRGGt/Ur9fv3dvDm1I1TADzs/zC2Z2xp4NYAK6uyCTwKIYQQQgghhBCicpM12yqLzFRY9zqsfFYNtNV8EF7eXaaBNoCdZ6K5ciMVFzsrHmniU+r3fyPtBsejjwPQ3rd9qd+/EEIIIYQQQggh7i+S2VYZxJxVp41GngA00HE8dHkXdGX/37ssWC2MMLBldWytdKV+/3uu7UFBoW6VunjZe5X6/QshhBBCCCGEEOL+UvbRGHF3jq1QM9oyk8HeAwbMhdrdyrpXAFy9mcq2U1EADC3Fwgh57bqyC4CO1TqWyf0LIYQQQgghhBDi/iLBtooqIwX+fhsOL1Fv+3eEAfPAufSnahbllwOXMCrQLtCdwKqOpX7/BqOBPdf2ANCxugTbhBBCCCGEEEIIce9JsK0iijqlThuNPglooPPb0Pkd0Jb+NM2iZBqM/PLvZQCGtSn9wggAx2OOE58ej5OVE02rNkUxKGXSDyGEEEIIIYQQQtw/JNhW0RxeBuvfhMwUcPCEJ36EWp3LulcFbAqJJDoxnapONvRsWDZrpe26qk4hbVetHXqtnkxDZpn0QwghhBBCCCH+v737Do+qTPs4/pv0BBJCaEloofdeA4QmzYKCiyBG6aACLypiQZQQFFkRFREFC0VXBMRFREVAkCA9CAZphg4CCVVIQoCUOe8f2YwM6WHCTMj3c11zLXPOc55zn3sGsrl9CoCig2JbYZF0VfrxeWn3orT3VTqkTRv1dsxF/9M3Rni0RUW5Ottn01vWawMAAAAAAHcaxTZHs35q2nTQDi/+c+zcAenbodKFg2nvO02QQp53qGmjNztyPkFbjlyUk0l6tKV9NkY4n3heBy4dkCS1K9/OLjEAAAAAAICih2Kbo3FyltZPSftz8LOqdHGDXOaPkFKupx1r8rh1Ic4BfbX9pCSpc+2yKu/raZcYNp3eJEmqX6q+SnmWsksMAAAAAACg6KHY5mjSC2nrp8h537dqcm7/P+faPit1DbdLWLl1PTlV3+w8Jcl+GyNI/6zXxi6kAAAAAADgTrLPYlrIXocXpTK15XRuvyz7Z3Z8xeELbZL0wx8xunItWRVKeqp9zTJ2iSHZnKytZ7ZKYr02AAAAAABwZ1Fsc1T9FsqQSSZJhrOb1PEle0eUK19uS9sYoX/LSnJ2MtklhqhzUUpITpCfh5/qla5nlxgAAAAAAEDRRLHNUe1bJpMMpZpcZEpNkjZMs3dEOdp7+oqi/rosV2eT+javaLc40qeQtg1sKycTX3EAAAAAAHDnsGabI9owTVo/RantX9YP8XX1gPd+OadvmuDAmyMs/N/GCN3r+auMt7vd4th4ivXaAAAAAACAfVBsczT/K7Sp0wSZ2zwnrVwpc8g4OTvftEupAxbc4q8n67uo05Kkx1vbb2OEmIQYHb58WE4mJ7UJbGO3OAAAAAAAQNFEsc3RmFOlThPSCmrJyf8cTy+wmVPtE1cOlv9+WolJqapetrhaVfGzWxzpU0gblWmkEu4l7BYHAAAAAAAomii2OZpO47M+54Aj2iTJMAzLFNLQVpVkMtlnYwTppimk7EIKAAAAAADsgNXjcdt2nvhbf8bGy8PVSQ83rWC3OG6k3tD22O2SWK8NAAAAAADYB8U23Lb0UW0PNgpUCU9Xu8WxM3anrqVcUxnPMqpVspbd4gAAAAAAAEUXxTbclktXk/TjHzGSpNBW9tsYQfpnvbaQCiF2ncoKAAAAAACKLoptuC3f7PxLSalmNShfQo0q+to1FkuxjfXaAAAAAACAnVBsQ76ZzdYbI9jTibgTOhF3Qi4mF7UOaG3XWAAAAAAAQNFFsQ35tunwBZ24mChvdxc92DjQvrGc3iRJalquqYq7FbdrLAAAAAAAoOii2IZ8W7j9hCTp4abl5eXmYtdYNp5iCikAAAAAALA/im3Il9gr17X2wDlJUmhr+26MkJicqB2xOySlbY4AAAAAAABgLxTbkC+Ld5xUqtlQyyp+qlnO266x7IjdoSRzkgKLBapqiap2jQUAAAAAABRtFNuQZympZi2O/EuS/TdGkG7ahbRCiEwmk52jAQAAAAAARRnFNuTZuj/PKTbuukoVc1OP+v52jcUwDMt6be0rtLdrLAAAAAAAABTbkGdfbkvbGOGR5hXl7uJs11iOXjmqM1fPyM3JTS38W9g1FgAAAAAAAPtuIYlC58TFq9p46IJMJumxlg4whfR/o9paBLSQp4unnaMBAAAAgPwxDEMpKSlKTU21dygAMuHs7CwXF5dcLV9FsQ158tX2k5Kk9jXKqFIpLztHc9N6beXZhRQAAABA4ZSUlKSYmBglJibaOxQA2fDy8lJAQIDc3NyybUexDbl2IyVVX/+WtjHC460r2zkaKSEpQbvO7pJEsQ0AAABA4WQ2m3Xs2DE5OzsrMDBQbm5ubPwGOBjDMJSUlKTz58/r2LFjqlGjhpycsl6ZjWIbcu2nPbH6OzFZASU81KlWGXuHo20x25RipCjIJ0iVfOw/pRUAAAAA8iopKUlms1kVK1aUl5f9Zw8ByJynp6dcXV114sQJJSUlycPDI8u2bJCAXFu4PW1jhP4tK8nF2f5fnfQppO3Kt7NzJAAAAABwe7IbJQPAMeT27yl/m5Erf8bGacfxv+XsZFK/FhXtHY4Mw7BsjhBSgSmkAAAAAADAMVBsQ66kb4zQrW45lfPJeqjknfLnpT91/tp5ebp4qnm55vYOBwAAAAAAQBLFNuTC1RspWrbrtCQptJX9N0aQ/plC2iqgldycs98FBAAAAACKglSzoa1HLuq7qNPaeuSiUs1Ggd6vY8eOevbZZwv0HrcjKChIM2bMsHcYBWLBggXy9fW1eb8mk0nLly+3eb9FDcU25GjF7jNKuJGiKqWLqU21UvYOR5L+mULKLqQAAAAAoFV7Y9TurV/U/9NtemZxlPp/uk3t3vpFq/bGFNg9ly1bptdffz1XbY8fPy6TyaSoqKgCi6cgLFu2TF27dlWZMmXk4+Oj4OBgrV69OtfXT5o0SSaTyepVu3btbK+JiIjIcE36a8eOHbf7SAVu0KBB6tWrV67ajhkzRs2aNZO7u7saN25coHHdSRTbkC3DMPTltrSNER5rWUlOTvbfgvry9cv648Ifkii2AQAAAMCqvTF6+stdirly3ep47JXrevrLXQVWcPPz85O3t3eB9J2d5OTkO3avX3/9VV27dtXKlSu1c+dOderUST179tTvv/+e6z7q1aunmJgYy2vTpk3Ztm/Tpo1V+5iYGA0bNkxVqlRR8+Z33zJKQ4YMUb9+/ewdhk1RbEO2ov66rH1n4uTm4qQ+zSrYOxxJ0pYzW2Q2zKruW10BxQPsHQ4AAAAA2JRhGEpMSsnVK/56ssJW7FNmE0bTj01asV/x15Nz1Z9h5H7q6c3TSIOCgvTmm29qyJAh8vb2VqVKlfTJJ59Y2lapUkWS1KRJE5lMJnXs2NFy7rPPPlOdOnXk4eGh2rVr66OPPrKcSx8Rt2TJEnXo0EEeHh5auHChZfTU9OnTFRAQoFKlSmnUqFHZFuJMJpM+/vhjPfDAA/Ly8lKdOnW0detWHT58WB07dlSxYsXUpk0bHTlyxHLNjBkz9OKLL6pFixaqUaOG3nzzTdWoUUPff/99rvPk4uIif39/y6t06dLZtndzc7NqX6pUKX333XcaPHiwTCbrATDLly9XjRo15OHhoe7du+uvv/7KMZ558+apXr16cnd3V0BAgEaPHm11/sKFC+rdu7e8vLxUo0YNrVixwnIuNTVVQ4cOVZUqVeTp6alatWrp/ffft5yfNGmSPv/8c3333XeW0XgRERFZxjJz5kyNGjVKVatWzfR8+nTZH374QbVq1ZKXl5f69OmjxMREff755woKClLJkiU1ZswYpaam5vjsd4qLvQOAY1v4v40RHmgQoJLFHGNttPT12tiFFAAAAMDd6FpyqupOzP1UxewYkmLjrqvBpDW5ar9/cnd5ueWvVPDOO+/o9ddf1yuvvKJvvvlGTz/9tDp06KBatWopMjJSLVu21Nq1a1WvXj25uaX9frlw4UJNnDhRs2bNUpMmTfT7779r+PDhKlasmAYOHGjp++WXX9Y777yjJk2ayMPDQxEREVq/fr0CAgK0fv16HT58WP369VPjxo01fPjwLGN8/fXX9e677+rdd9/VSy+9pMcee0xVq1bV+PHjValSJQ0ZMkSjR4/WTz/9lOn1ZrNZ8fHx8vPzy3VeDh06pMDAQHl4eCg4OFhTp05VpUqVcn39ihUrdPHiRQ0ePNjqeGJioqZMmaIvvvhCbm5uGjlypB599FFt3rw5y75mz56tsWPH6t///rfuvfdeXblyJUP78PBwTZs2TW+//bY++OADhYaG6sSJE/Lz85PZbFaFChW0dOlSlSpVSlu2bNGIESMUEBCgvn37aty4cTpw4IDi4uI0f/58ScpTrjKTmJiomTNnavHixYqPj9fDDz+s3r17y9fXVytXrtTRo0f1r3/9S23btnWYEXIU25Cly4lJ+n73GUlSaGvH2Bgh1ZyqzafT/iFgCikAAAAAOI777rtPI0eOlCS99NJLeu+997R+/XrVqlVLZcqUkSSVKlVK/v7+lmvCwsL0zjvv6OGHH5aUNgJu//79+vjjj62Kbc8++6ylTbqSJUtq1qxZcnZ2Vu3atXX//fdr3bp12RbbBg8erL59+1piDA4O1muvvabu3btLkp555pkMRa2bTZ8+XQkJCZY+ctKqVSstWLBAtWrVUkxMjMLDwxUSEqK9e/fmegru3Llz1b17d1WoYD3bLDk5WbNmzVKrVq0kSZ9//rnq1KljKWxm5o033tDzzz+vZ555xnKsRYsWVm0GDRqk/v37S5LefPNNzZw5U5GRkerRo4dcXV0VHh5uaVulShVt3bpVX3/9tfr27avixYvL09NTN27csPqcb0dycrJmz56tatWqSZL69Omj//znPzp79qyKFy+uunXrqlOnTlq/fj3FNji+/+46rRspZtX291bTSr72DkeStO/iPv19428Vdy2uxmUb2zscAAAAALA5T1dn7Z/cPVdtI49d0qD5OS+av2BwC7WskvMII09X51zdNzMNGza0/NlkMsnf31/nzp3Lsv3Vq1d15MgRDR061KpAlpKSohIlSli1zWytsnr16snZ+Z94AwICtGfPnlzHWK5cOUlSgwYNrI5dv35dcXFx8vHxsbr2q6++Unh4uL777juVLVs22/uku/fee63u3apVK1WuXFlff/21hg4dqqeeekpffvmlpU1CQoLV9adOndLq1av19ddfZ+jbxcXFqlBWu3Zt+fr66sCBA/L391fdunUt51555RUNGzZMZ86c0T333JNtzDfnqFixYvLx8bH6HD/88EPNmzdPJ0+e1LVr15SUlJTj5gb33nuvNm5Mm6VWuXJl7du3L9v2N/Py8rIU2qS0zygoKEjFixe3Opbdd+1Oo9iGTBmGoYXb0zZGeLx15Qzzwu0lfQppcGCwXJ1c7RwNAAAAANieyWTK9VTOkBplFFDCQ7FXrme6bptJkn8JD4XUKCPnAt7wztXV+nc0k8kks9mcZfv0wtKnn35qGZ2V7uYimpRW9Lnd+916TfrvuZkdu7WfxYsXa9iwYVq6dKm6dOmS7T2y4+vrq5o1a+rw4cOSpMmTJ2vcuHFZtp8/f75KlSqlBx98ME/3CQwMtNr51c/PL0O+spJdXhcvXqxx48bpnXfeUXBwsLy9vfX2229r+/bt2fb52Wef6dq1a5n2n5948vPZ30kU25CprUcv6uj5qyrm5qxeTcrbOxyLjafSim3tK7S3cyQAAAAAYH/OTiaF9ayrp7/cJZNkVXBLL62F9axb4IW2nKSv0XbzIvblypVTYGCgjh49qtDQUHuFlqNFixZpyJAhWrx4se6///7b6ishIUFHjhzRE088IUkqW7ZslqPkDMPQ/PnzNWDAgEwLVCkpKfrtt98sU0ajo6N1+fJl1alTRy4uLqpevXqGa4KCgrRu3Tp16tQpX/Fv3rxZbdq0sUwXlmS1oYSU9lnfullB+fKOU1e4E/K1G2lKSorWrl2rjz/+WPHx8ZKkM2fOZBjuiMJr4ba0jRF6NSmv4u6OUZO9cO2C9l1MG2rarnw7O0cDAAAAAI6hR/0AzX68qfxLeFgd9y/hodmPN1WP+gF2iuwfZcuWlaenp1atWqWzZ8/qypUrktIW4586dapmzpypgwcPas+ePZo/f77effddO0ec5quvvtKAAQP0zjvvqFWrVoqNjVVsbKwl/pyMGzdOGzZs0PHjx7Vlyxb17t1bzs7OljXRsvPLL7/o2LFjGjZsWKbnXV1d9X//93/avn27du7cqUGDBql169ZZrtcmpe0W+s4772jmzJk6dOiQdu3apQ8++CBXzyJJNWrU0G+//abVq1fr4MGDeu2117Rjh/U05qCgIP3xxx+Kjo7WhQsXst0h9vDhw4qKilJsbKyuXbumqKgoRUVFKSkpKdcxOaI8V1FOnDihHj166OTJk7px44a6du0qb29vvfXWW7px44bmzJlTEHHiDjoXf12r98VKkkJbOcbGCJIsGyPULVVXpT2z3yoZAAAAAIqSHvUD1LWuvyKPXdK5+Osq6+2hllX87D6iLZ2Li4tmzpypyZMna+LEiQoJCVFERISGDRsmLy8vvf3223rhhRdUrFgxNWjQQM8++6y9Q5YkffLJJ0pJSdGoUaM0atQoy/GBAwdqwYIFOV5/6tQp9e/fXxcvXlSZMmXUrl07bdu2zbJhRHbmzp2rNm3aqHbt2pme9/Lysuyoevr0aYWEhGju3LnZ9jlw4EBdv35d7733nsaNG6fSpUurT58+OcaS7sknn9Tvv/+ufv36yWQyqX///ho5cqTV7q3Dhw9XRESEmjdvroSEBK1fv14dO3bMtL9hw4Zpw4YNlvdNmjSRJB07dkxBQUG5jsvRmAzDyGxad5Z69eolb29vzZ07V6VKldLu3btVtWpVRUREaPjw4Tp06FBBxWoTcXFxKlGihK5cuZJhsUNHk5ycrJUrV+q+++7L85zm2zHrl0Oavuagmlby1bKRbe/YfXMybsM4rT6+Wk82fFKjm4zO8/X2yufdjJzaFvm0PXJqW+TT9sipbZFP2yOntkU+ba+w5DS730OvX7+uY8eOqUqVKvLw8MiiBwCOILd/X/M8sm3jxo3asmWLZb51uqCgIJ0+fTrvkcKhpJoNLYr8S1LaxgiOIsWcoi2nt0iSQiqE2DkaAAAAAACAzOV5zTaz2ZxhoTspbWikt7e3TYKC/UREn9Ppy9fk6+Wq+xrYf15/ut3ndys+OV6+7r6qX6q+vcMBAAAAABRxJ0+eVPHixbN8nTx50t4hwk7yPLKtW7dumjFjhj755BNJadurJiQkKCwsTPfdd5/NA8SdtXB72j8GjzSrIA9X5xxa3znpu5C2Ld9Wzk6OExcAAAAAoGgKDAxUVFRUtudRNOW52DZ9+nT16NFDdevW1fXr1/XYY4/p0KFDKl26tBYtWlQQMeIO+etSotZHn5MkPeZAGyNI0sbTacW2kPJMIQUAAAAA2J+Li4uqV69u7zDggPJcbKtYsaJ2796tJUuWaPfu3UpISNDQoUMVGhoqT0/PgogRd8jiHSdlGFK76qVVpXQxe4djEXs1Vgf/PiiTTGob6DgbNgAAAAAAANwqT8W25ORk1a5dWz/88INCQ0MVGhpaUHHhDktKMWvJjrSNEUJbVbJzNNbSR7U1LNNQvh6+9g0GAAAAAAAgG3naIMHV1VXXr18vqFhgR2v2x+pCQpLKerurS91y9g7HSvp6bUwhBQAAAAAAji7Pu5GOGjVKb731llJSUgoiHtjJl9tOSJIebVFRrs55/loUmKTUJG2L2SZJCqlAsQ0AAAAAADi2PK/ZtmPHDq1bt05r1qxRgwYNVKyY9dpey5Yts1lwuDMOn4vXtqOX5GSSHm3pWFNId57dqWsp11Tas7Rq+9W2dzgAAAAAAADZynOxzdfXV//6178KIhbYycLtJyVJnWuXU6CvY21ykb5eW7vy7eRkcpwRdwAAAAAAAJnJc/Vi/vz52b5QuFxLStV/d56SJD3e2rFGtUms1wYAAAAAOVo/VdowLfNzG6alnS8gf/31l4YMGaLAwEC5ubmpcuXKeuaZZ3Tx4sUCu2dOdu/erf79+6tixYry9PRUnTp19P777+d4XceOHWUymTK87r///izblCtXTo888ohOnDiRbd8REREymUy6fPny7T6eJGnSpElq3LixTfrKjaCgIM2YMeOO3a+wy/dQofPnz2vTpk3atGmTzp8/b8uYcAd9/8cZxV1PUUU/T7WvUcbe4Vj5K+4vHY87LmeTs4IDg+0dDgAAAAA4Jidnaf2UjAW3DdPSjjs5F8htjx49qubNm+vQoUNatGiRDh8+rDlz5mjdunUKDg7WpUuXCuS+Odm5c6fKli2rL7/8Uvv27dOECRM0fvx4zZo1K9vrli1bppiYGMtr7969cnZ21iOPPGLVbvjw4YqJidGZM2f03Xff6a+//tLjjz9ekI+Ub8nJyfYOoUjKc7Ht6tWrGjJkiAICAtS+fXu1b99egYGBGjp0qBITEwsiRhSghf/bGOGxlpXl5GSyczTW0qeQNinbRN5u3naOBgAAAADuEMOQkq7m/hU8Smr/Qlph7Zc30o798kba+/YvpJ3PbV+GkeswR40aJTc3N61Zs0YdOnRQpUqVdO+992rt2rU6ffq0JkyYoFmzZql+/fqWa5YvXy6TyaQ5c+ZYjnXp0kWvvvqq5f13332npk2bysPDQ1WrVlV4eLjVJo0mk0mfffaZevfuLS8vL9WoUUMrVqywnB8yZIjef/99dejQQVWrVtXjjz+uwYMH57jGvJ+fn/z9/S2vn3/+WV5eXhmKbV5eXvL391dAQIBat26t0aNHa9euXbnOmyQtWLBAvr6+Wr16terUqaPixYurR48eiomJsbSJiIhQy5YtVaxYMfn6+qpt27Y6ceKEFixYoPDwcO3evdsywm7BggWW3MyePVsPPvigihUrpilTpljudbP0z+Fm33//vVq0aCEPDw+VLl1avXv3lpQ2mu/EiRN67rnnLPdD9vK8ZtvYsWO1YcMGff/992rbtq0kadOmTRozZoyef/55zZ492+ZBomDsOXVFu09dkauzSY80r2DvcDJIL7axCykAAACAIiU5UXozMH/X/vp22iur9zl55YzkVizHZpcuXdLq1as1ZcoUeXpar/3t7++v0NBQLVmyRBs2bNCYMWN0/vx5lSlTRhs2bFDp0qUVERGhp556SsnJydq6datefvllSdLGjRs1YMAAzZw5UyEhITpy5IhGjBghSQoLC7PcIzw8XNOmTdPbb7+tDz74QKGhoTpx4oT8/PwyjffKlStZnsvK3Llz9eijj2bYGPLWPHz99ddq1apVnvqWpMTERE2fPl3/+c9/5OTkpMcff1zjxo3TwoULlZKSol69emn48OFatGiRkpKSFBkZKZPJpH79+mnv3r1atWqV1q5dK0kqUaKEpd9Jkybp3//+t2bMmCEXFxf98ssvOcby448/qnfv3powYYK++OILJSUlaeXKlZLSRvw1atRII0aM0PDhw/P8nEVRnott//3vf/XNN9+oY8eOlmP33XefPD091bdvX4pthcjC7Wmj2u6tH6DSxd3tHI21aynXtCN2hyTWawMAAAAAR3Po0CEZhqE6depker5OnTr6+++/VbZsWfn5+WnDhg3q06ePIiIi9Pzzz1vWUIuMjFRycrLatGkjKa2I9vLLL2vgwIGSpKpVq+r111/Xiy++aFVsGzRokPr37y9JevPNNzVz5kxFRkaqR48eGWLZsmWLlixZoh9//DHXzxcZGam9e/dq7ty5Gc599NFH+uyzz2QYhhITE1WzZk2tXr06132nS05O1pw5c1StWjVJ0ujRozV58mRJUlxcnK5cuaIHHnjAcv7mXBcvXlwuLi7y9/fP0O9jjz2mwYMH5ymWKVOm6NFHH1V4eLjlWKNGjSSljfhzdnaWt7d3pvdDRnkutiUmJqpcuXIZjpctW5ZppIVI3PVkfRd1RpIU2srxNkbYEbtDN1JvKKBYgKr7Vrd3OAAAAABw57h6pY0wy6tN76WNYnN2k1KT0qaQtnsu7/fOAyOHaafu7u5q3769IiIi1KVLF+3fv18jR47UtGnT9Oeff2rDhg1q0aKFvLzS7rt7925t3rxZU6ZMsfSRmpqq69evKzEx0dKuYcOGlvPFihWTj4+Pzp07l+H+e/fu1UMPPaSwsDB169ZNknTy5EnVrVvX0uaVV17RK6+8YnXd3Llz1aBBA7Vs2TJDn6GhoZowYYIk6ezZs3rzzTfVrVs37dy5U97e3qpXr55lw4SQkBD99NNPmebGy8vLUkiTpICAAMsz+Pn5adCgQerevbu6du2qLl26qG/fvgoICMgq1RbNmzfPsc2toqKiGLVmQ3kutgUHByssLExffPGFPDw8JEnXrl1TeHi4goNZxL6w+HbXaV1LTlXNcsXVskrehtLeCTfvQsp8cAAAAABFismUq6mcVjZMSyu0dZogdXjxn80RnN3S3ttY9erVZTKZdODAAcvaXjc7cOCAypQpI19fX3Xs2FGffPKJNm7cqCZNmsjHx8dSgNuwYYM6dOhguS4hIUHh4eF6+OGHM/SZXoOQJFdXV6tzJpNJZrPZ6tj+/ft1zz33aMSIEVZrwgUGBioqKsry/tbppVevXtXixYsto8xuVaJECVWvXt2Sh7lz5yogIEBLlizRsGHDtHLlSsvGBLdOsb1ZZs9wc/Fy/vz5GjNmjFatWqUlS5bo1Vdf1c8//6zWrVtn2aekDNNenZycMhRFb904Ibs4kXd5Lra9//776t69uypUqGAZUrh79255eHjka9gk7jzDMCxTSENbVXa4YpZhGKzXBgAAAAC5lV5YSy+0Sf/87/op1u9tpFSpUuratas++ugjPffcc1bFmtjYWC1cuFCjRo1Ku3WHDnr22We1dOlSy5JUHTt21Nq1a7V582Y9//zzlmubNm2q6OhoSzErv/bt26fOnTtr4MCBVqPkJMnFxSXb/pcuXaobN27keodRZ+e03V6vXbsmSapcuXI+o86oSZMmatKkicaPH6/g4GB99dVXat26tdzc3JSampqrPsqUKaP4+HhdvXrVUoi7udgopY0UXLduXZbTT/NyP+Sj2Fa/fn0dOnRICxcu1J9//ilJ6t+/v0JDQ6mEFhI7jv+tg2cT5OnqrN5Ny9s7nAyOxR3T6YTTcnVyVUv/jEN2AQAAAAA3MadaF9rSpb83F0yRZNasWWrTpo26d++uN954Q1WqVNG+ffv0wgsvqGbNmpo4caKktEJOyZIl9dVXX+mHH36QlFZsGzdunEwmk2XzRUmaOHGiHnjgAVWqVEl9+vSRk5OTdu/erb179+qNN97IVVx79+5V586d1b17d40dO1axsbGS0opiZcqUyfH6uXPnqlevXipVqlSm5xMTEy19nj17Vq+//ro8PDws01Rt4dixY/rkk0/04IMPKjAwUNHR0Tp06JAGDBggSQoKCtKxY8cUFRWlChUqyNvbW+7uma/F3qpVK3l5eemVV17RmDFjtH37dsvupenCwsJ0zz33qFq1anr00UeVkpKilStX6qWXXrLc79dff9Wjjz4qd3d3lS5d2mbPejdyys9FXl5eGj58uN555x298847GjZsWL4LbR9++KGCgoLk4eGhVq1aKTIyMtv2ly9f1qhRoxQQECB3d3fVrFnTskMGcid9VNtDjQPl4+GaQ+s7L30KaQv/FvLK43oBAAAAAFDkdBqf9ci1Di+mnS8ANWrU0I4dO1S1alX17dtXlStX1r333quaNWtq8+bNKl68uKS06ZEhIWlLBLVr105SWgHOx8dHzZs3t5r22L17d/3www9as2aNWrRoodatW+u9997L02ixb775RufPn9eXX36pgIAAy6tFixY5XhsdHa1NmzZp6NChWbb59NNPLX126tRJFy5c0MqVK1WrVq1cx5gTLy8v/fnnn/rXv/6lmjVrasSIERo1apSefPJJSdK//vUv9ejRQ506dVKZMmW0aNGiLPvy8/PTl19+qZUrV6pBgwZatGiRJk2aZNWmY8eOWrp0qVasWKHGjRurc+fOVvWZyZMn6/jx46pWrVquCpZFXZ5Htk2dOlXlypXTkCFDrI7PmzdP58+ft1Q9c2PJkiUaO3as5syZo1atWmnGjBnq3r27oqOjVbZs2Qztk5KS1LVrV5UtW1bffPONypcvrxMnTsjX1zevj1FkXUy4oZ/2pFXgQ1vZbmirLVmmkLILKQAAAAA4tKCgIKtRUmFhYXr33Xf1xx9/WK0ttnz5cqvrnJycdOnSpUz77N69u7p3757lPTPblOHy5cuWP0+aNClDMSm3atWqle2mDxEREfnqt2PHjlb9Dho0SIMGDbJq06tXL0ubcuXK6dtvv82yP3d3d33zzTcZjmcVe69evdSrVy+rY7duiPDwww9nulaeJLVu3Vq7d+/OMh5Yy/PIto8//li1a9fOcLxevXqaM2dOnvp69913NXz4cA0ePFh169bVnDlz5OXlpXnz5mXaft68ebp06ZKWL1+utm3bKigoSB06dLCsHYecLd15SkmpZjWqUEINKpSwdzgZXE2+qp1nd0pivTYAAAAAKGzCw8M1c+ZMbdu2LcOGBUBRkeeRbbGxsZluNVumTBnFxMTkup+kpCTt3LlT48f/M5zVyclJXbp00datWzO9ZsWKFQoODtaoUaP03XffqUyZMnrsscf00ksvWRYkvNWNGzd048YNy/u4uDhJaTtv3Lr7hqNJj89WcZrNhhZuS5tC2q95BYd8/s1/bVaKOUUVi1dUoGegTWO0dT5BTm2NfNoeObUt8ml75NS2yKftkVPbIp+2V1hy6ujx2VpWi+wDRUWei20VK1bU5s2bVaVKFavjmzdvVmBgYK77uXDhglJTU1WuXDmr4+XKlbNsvHCro0eP6pdfflFoaKhWrlypw4cPa+TIkUpOTlZYWFim10ydOlXh4eEZjq9Zs0ZeXoVjPbCff/7ZJv0cuGzSX387y9PZkOuZ3Vp51vGGgC5PXC5JqpBUocDW4rNVPvEPcmpb5NP2yKltkU/bI6e2RT5tj5zaFvm0PUfPaWJior1DAHAH5bnYNnz4cD377LNKTk5W586dJUnr1q3Tiy++aLVdb0Ewm80qW7asPvnkEzk7O6tZs2Y6ffq03n777SyLbePHj9fYsWMt7+Pi4lSxYkV169ZNPj4+BRrv7UpOTtbPP/+srl27ytX19jcy+H7h75LO65EWldXr/oxTge3NMAzNXD5TkhTaJlRtAtvYtH9b5xPk1NbIp+2RU9sin7ZHTm2LfNoeObUt8ml7hSWn6TOsABQNeS62vfDCC7p48aJGjhyppKQkSZKHh4deeuklqymhOSldurScnZ119uxZq+Nnz56Vv79/ptcEBATI1dXVasponTp1FBsbq6SkJLm5uWW4xt3dPdPtb11dXR36H+Ob2SLWM5ev6Zfo85KkAW2CHPLZoy9F69y1c/Jw9lDrCq3l6lwwMRamz76wIKe2RT5tj5zaFvm0PXJqW+TT9sipbZFP23P0nDpybABsL88bJJhMJr311ls6f/68tm3bpt27d+vSpUuaOHFinvpxc3NTs2bNtG7dOssxs9msdevWKTg4ONNr2rZtq8OHD1stsnjw4EEFBARkWmjDPxbv+EtmQ2pVxU/Vy3rbO5xMpe9C2iqgldydMxZIAQAAAAAAHF2ei23pihcvrhYtWsjb21tHjhzJ1y4jY8eO1aeffqrPP/9cBw4c0NNPP62rV69aFlMcMGCA1Wi5p59+WpcuXdIzzzyjgwcP6scff9Sbb76pUaNG5fcxioTkVLMWR56UJD3eurKdo8naxlNpxbaQ8uxCCgAAAAAACqdcTyOdN2+eLl++bLX+2YgRIzR37lxJUq1atbR69WpVrFgx1zfv16+fzp8/r4kTJyo2NlaNGzfWqlWrLJsmnDx5Uk5O/9QDK1asqNWrV+u5555Tw4YNVb58eT3zzDN66aWXcn3PomjdgbM6F39DpYu7qXu9zKfo2tuVG1cUdT5KktSuQjv7BgMAAAAAAJBPuS62ffLJJ3ryySct71etWqX58+friy++UJ06dTR69GiFh4frs88+y1MAo0eP1ujRozM9FxERkeFYcHCwtm3blqd7FHVfbksb1da3eUW5ueR7MGOB2npmq8yGWdVKVFP54uXtHQ4AAAAAAEC+5LrycujQITVv3tzy/rvvvtNDDz2k0NBQNW3aVG+++abV+mtwDMcuXNWmwxdkMkn9W1aydzhZSl+vLaQCU0gBAAAAoLAzmUxavny5vcMochYsWCBfX99s2wwaNEi9evW6I/EUtIiICJlMJl2+fNneoVjJdbHt2rVr8vHxsbzfsmWL2rdvb3lftWpVxcbG2jY63Lavtp+QJHWsWUYV/bzsHE3mzIZZm05vksR6bQAAAABwO7ae2aqHlj+krWe2Fvi9CkPRJjo6Wp06dVK5cuXk4eGhqlWr6tVXX1VycnK2140ZM0bNmjWTu7u7GjdunOv7LVy4UI0aNZKXl5cCAgI0ZMgQXbx40XJ+0qRJMplMlleJEiUUEhKiDRs25Kr/9evX67777lOpUqXk5eWlunXr6vnnn9fp06dzHeP777+vBQsW5Lq9Pf3+++965JFHLJ9fjRo1NHz4cB08eNCm9wkKCtKMGTNs1l+ui22VK1fWzp07JUkXLlzQvn371LZtW8v52NhYlShRwmaB4fZdT07V0p2nJEmhrRx3Y4T9F/fr0vVLKuZaTE3KNrF3OAAAAABQKBmGofd3va+jV47q/V3vyzAMe4dkd66urhowYIDWrFmj6OhozZgxQ59++qnCwsJyvHbIkCHq169fru+1efNmDRgwQEOHDtW+ffu0dOlSRUZGavjw4Vbt6tWrp5iYGMXExGjr1q2qUaOGHnjgAV25ciXb/j/++GN16dJF/v7++u9//6v9+/drzpw5unLlit55551cx1miRIkcR785gh9++EGtW7fWjRs3tHDhQh04cEBffvmlSpQooddee83e4WUr18W2gQMHatSoUXr99df1yCOPqHbt2mrWrJnl/JYtW1S/fv0CCRL5s3JPjC4nJiuwhIc61S5r73CylL4LaZvANnJ1drVzNAAAAABgX4ZhKDE5Mc+v9SfXa9/FfZKkfRf3af3J9Xnuo6AKdC+99JJq1qwpLy8vVa1aVa+99prV6LJJkyapcePGmjdvnipVqqTixYtr5MiRSk1N1bRp0+Tv76+yZctqypQpVv2+++67atCggYoVK6aKFStq5MiRSkhIsJyvWrWqBg8erEaNGqly5cp68MEHFRoaqo0bN2Yb78yZMzVq1ChVrVo118+4detWBQUFacyYMapSpYratWunJ598UpGRkVbtXFxc5O/vL39/f9WtW1eTJ09WQkJCtqO1Tp06pTFjxmjMmDGaN2+eOnbsqKCgILVv316fffaZJk6caNV+9erVqlOnjooXL64ePXooJibGcu7WEYkdO3bUmDFj9OKLL8rPz0/+/v6aNGmSVX+XL1/WsGHDVKZMGfn4+Khz587avXu35fzu3bvVqVMneXt7y8fHR82aNdNvv/1mOb9p0yaFhITI09NTFStW1JgxY3T16tUsnzcxMVGDBw/WfffdpxUrVqhLly6qUqWKWrVqpenTp+vjjz+2ar9z5041b95cXl5eatOmjaKjoy3njhw5ooceekjlypVT8eLF1aJFC61du9bq+U+cOKHnnnvOMuLwduV6g4QXX3xRiYmJWrZsmfz9/bV06VKr85s3b1b//v1vOyDYzsLtaRsj9G9ZSc5Ot/9lKSiW9dqYQgoAAAAAupZyTa2+anXb/TwT8Uyer9n+2HZ5udp+CSJvb28tWLBAgYGB2rNnj4YPHy5vb2+9+OKLljZHjhzRTz/9pFWrVunIkSPq06ePjh49qpo1a2rDhg3asmWLhgwZoi5duqhVq7T8ODk5aebMmapSpYqOHj2qkSNH6sUXX9RHH32UaRyHDx/WqlWr9PDDD9v8GYODg/XKK69o5cqVuvfee3Xu3Dl98803uu+++7K85saNG5o/f758fX1Vq1atLNstXbpUSUlJVvm62c0j1RITEzV9+nT95z//kZOTkx5//HGNGzdOCxcuzLL/zz//XGPHjtX27du1detWDRo0SG3btlXXrl0lSY888og8PT31008/qUSJEvr44491zz336ODBg/Lz81NoaKiaNGmi2bNny9nZWVFRUXJ1TRtMc+TIEfXo0UNvvPGG5s2bp/Pnz1s2y5w/f36m8axevVoXLlzI1fNK0oQJE/TOO++oTJkyeuqppzRkyBBt3rxZkpSQkKD77rtPU6ZMkbu7u7744gv17NlT0dHRqlSpkpYtW6ZGjRppxIgRGUYh5leui21OTk6aPHmyJk+enOn5W4tvsK8DMXHaeeJvuTiZ1K9lRXuHk6WL1y5q74W9kqS25dvm0BoAAAAAUBi9+uqrlj8HBQVp3LhxWrx4sVUxxWw2a968efL29lbdunXVqVMnRUdHa+XKlXJyclKtWrX01ltvaf369ZZi27PPPmvV7xtvvKGnnnoqQ7GtTZs22rVrl27cuKERI0ZkWdu4HW3bttXChQvVr18/Xb9+XSkpKerZs6c+/PBDq3Z79uxR8eLFJaUVxry9vbVkyRKrdfJvdejQIfn4+CggICDHOJKTkzVnzhxVq1ZNkjR69Ogcn7dhw4aWqbU1atTQrFmztG7dOnXt2lWbNm1SZGSkzp07J3d3d0nS9OnTtXz5cn3zzTcaMWKETp48qRdeeEG1a9e29JFu6tSpCg0NtXxWNWrU0MyZM9WhQwfNnj1bHh4emT6vJEt/OZkyZYo6dOggSXr55Zd1//336/r16/Lw8FCjRo3UqFEjS9vXX39d3377rVasWKHRo0fLz89Pzs7O8vb2lr+/f67ul5NcF9tQuCz838YI3ev5q6x3xi+uo9hyZosMGarjV0dlvRx3qisAAAAA3CmeLp7a/tj2XLc3DEODVw9W9N/RMhtmy3Enk5Nqlayl+d3n53pqnKeLZ57jzY0lS5Zo5syZOnLkiBISEpSSkpKhuBQUFCRvb2/L+3LlysnZ2VlOTk5Wx86dO2d5v3btWk2dOlV//vmn4uLilJKSouvXrysxMVFeXv+M0FuyZIni4+O1e/duvfDCC5o+fXqWo6ZyI71YJkmPP/645syZo/379+uZZ57RxIkT1b17d8XExOiFF17QU089pblz51ra16pVSytWrJAkxcfHa8mSJXrkkUe0fv16NW/eXE899ZS+/PJLS/uEhAQZhpHrz9DLy8tSaJOkgIAAq5xlpmHDhlbvb75m9+7dSkhIUKlSpazaXLt2TUeOHJEkjR07VsOGDdN//vMfdenSRY888oglht27d+uPP/6wGllnGIbMZrOOHTumb7/9Vm+++abl3P79+/M8nfnm+NMLkufOnVOlSpWUkJCgSZMm6ccff1RMTIxSUlJ07do1nTx5Mk/3yAuKbXehhBsp+nZX2k4koa0q2Tma7KWv19aufDs7RwIAAAAAjsFkMuVpKufm05t14NKBDMfNhlkHLh1Q1Pkou84k2rp1q0JDQxUeHq7u3burRIkSWrx4cYZF/dOnHaYzmUyZHjOb0wqKx48f1wMPPKCnn35aU6ZMkZ+fnzZt2qShQ4cqKSnJqthWsWLajK+6desqNTVVI0aM0PPPPy9nZ+d8PVNUVJTlz+lFw6lTp6pt27Z64YUXJKUVgIoVK6aQkBC98cYbliKQm5ubqlevbrm+SZMmWr58uWbMmKEvv/xSkydP1rhx46zuV7NmTV25ckUxMTE5jm7LLGc5Fa+yy3NCQoICAgIUERGR4br06ZyTJk3SY489ph9//FE//fSTwsLCtHjxYvXu3VsJCQl68sknNWbMmAzXV6pUSU899ZT69u1rORYYGKiaNWtKkv78808FBwdnG/ut8acXJdPjHzdunH7++WdNnz5d1atXl6enp/r06aOkpKQc+80vim13oe+iTutqUqqqli6m4Gqlcr7ATlLMKdp8Jm0OdfsK7e0cDQAAAAAUPoZh6IPfP5BJJhnKWFAxyaQPfv9AbQLb2GTh9/zYsmWLKleurAkTJliOnThx4rb73blzp8xms9555x3L6Levv/46x+vMZrOSk5NlNpvzXWy7uViWLjExUS4u1mWW9P5zKnY5Ozvr2rVrkqSyZcuqbFnrmV99+vTRyy+/rGnTpum9997LcP3ly5cLbIfRpk2bKjY2Vi4uLgoKCsqyXc2aNVWzZk0999xz6t+/v+bPn6/evXuradOm2r9/f6Y5kyQ/Pz/5+flZHevWrZtKly6tadOm6dtvv81wTV6ed/PmzRo0aJB69+4tKa14ePz4cas2bm5uSk1NzVV/uUGx7S5jGIa+3JY2FPKxVpXs9o9pbuy5sEdxSXEq4V5CDUo3sHc4AAAAAFDoJJuTFXs1NtNCmyQZMhR7NVbJ5mS5ObvZ/P5XrlyxGuUlKcN0wxo1aujkyZNavHixWrRooR9//DHTAkpeVa9eXcnJyfrggw/Us2dPbd68WXPmzLFqs3DhQrm6uqpBgwZyd3fXb7/9pvHjx6tfv36W0VDffvutxo8frz///NNy3eHDh5WQkKDY2Fhdu3bN8ox169aVm1vmeezZs6eGDx+u2bNnW6aRPvvss2rZsqUCAwMt7VJSUhQbGyvpn2mk+/fv10svvZTls1asWFHvvfeeRo8erbi4OA0YMEBBQUE6deqUvvjiCxUvXjzDSEFb6dKli4KDg9WrVy9NmzZNNWvW1JkzZ/Tjjz+qd+/eqlevnl544QX16dNHVapU0alTp7Rjxw7961//kpS2E23r1q01evRoDRs2TMWKFdP+/fv1888/a9asWZnes1ixYvrss8/0yCOP6MEHH9SYMWNUvXp1XbhwQV9//bXl+5QbNWrU0LJly9SzZ0+ZTCa99tprllFv6YKCgvTrr7/q0Ucflbu7u0qXLn1bOaPYdpf5/a/LOhATJ3cXJ/VpVsHe4WQrfQppm8A2cnbK339NAAAAAICizM3ZTYsfWKxL1y9l2cbPw69ACm2SFBERoSZNmlgdGzp0qNX7Bx98UM8995xGjx6tGzdu6P7779drr72mSZMm3da9GzVqpHfffVdvvfWWxo8fr/bt22vq1KkaMGCApY2Li4veeustHTx4UIZhqHLlyho9erSee+45S5srV64oOjraqu9hw4Zpw4YNlvfpz3js2LEsR3cNGjRI8fHxmjVrlp5//nn5+vqqc+fOeuutt6za7du3zzIVNH19tdmzZ1vFnZmRI0eqZs2amj59unr37q1r164pKChIDzzwgMaOHZtzwvLJZDJp5cqVmjBhggYPHqzz58/L399f7du3t6yrd/HiRQ0YMEBnz55V6dKl9fDDDys8PFxS2nTaDRs2aMKECQoJCZFhGKpWrZr69euX7X0feughbdmyRVOnTtVjjz2muLg4VaxYUZ07d9Ybb7yR6/jfffddDRkyRG3atFHp0qX10ksvKS4uzqrN5MmT9eSTT6patWq6ceNGnteMu5XJuN0e/uevv/5SWFiY5s2bZ4vuCkxcXJxKlCihK1euZLvThyNITk7WypUrdd9992WYP52VsV9Hadmu0/pX0wp6p2+jnC+wo0e+f0R/XvpTb7Z7Uz2r9Szw++Unn8geObUt8ml75NS2yKftkVPbIp+2R05ti3zaXmHJaXa/h16/fl3Hjh1TlSpVMt2VEYDjyO3fV6csz+TRpUuX9Pnnn9uqO+TD31eT9MMfMZKkx1s79sYIZ6+e1Z+X/pRJJrsu1AkAAAAAAGBLuZ5Gmr4tbVaOHj1628Hg9vx31yklpZhVN8BHjSv62jucbKVvjNCgdAP5efjl0BoAAAAAAKBwyHWxrVevXjluF+vIi/Hf7cxmQwu3p22M8Hjryg7/Wfx66ldJUrsK7ewcCQAAAAAAgO3kehppQECAli1bJrPZnOlr165dBRkncrD16EUdu3BVxd1d9FDjwJwvsKPk1GRtPbNVktS+fHs7RwMAAAAAAGA7uS62NWvWTDt37szyfE6j3lCwvtx2QpLUu0l5FXN37E1md53bpcSURPl5+KlOqTr2DgcAAAAAAMBmcl2VeeGFF3T16tUsz1evXl3r16+3SVDIm7Nx17Vm/1lJUqiDb4wgSRtPbZQktSvfTk4mm+3RAQAAAAAAYHe5LraFhIRke75YsWLq0KHDbQeEvFuy4y+lmg01r1xStf19cr7AzjaeTiu2hVTI/jsFAAAAAABQ2OR6WNHRo0eZJuqAUlLNWhSZtjFCYRjVdir+lI5eOSpnk7OCA4LtHQ4AAAAAAIBN5brYVqNGDZ0/f97yvl+/fjp79myBBIXcWx99XjFXrqukl6vurR9g73BytOn0JklSozKNVMK9hJ2jAQAAAIC7S9xPP+lguxDFrVpl71CAIivXxbZbR7WtXLky2zXccGcs3J62McIjzSvKw9XZztHkjCmkAAAAAFAwUi5eVMzEMKVeuKCYiWFKuXjR3iEBRRKr0xdif11K1IaDaaMNH2vp+FNIr6dcV2RMpCSpfYX2do4GAAAAAO4ehmEodtIkmRMTJUnmq1cVOym8wO/7119/aciQIQoMDJSbm5sqV66sZ555RhftWOjbvXu3+vfvr4oVK8rT01N16tTR+++/n+N1HTt2lMlkyvC6//77JUnJycl66aWX1KBBAxUrVkyBgYEaMGCAzpw5Y9XPzde6uLioUqVKGjt2rG7cuJHt/SdNmqTGjRvn+7kze55nn33WZv1l5/jx4zKZTIqKiroj93N0uS62pX9Rbj0G+/kq8qQMQwqpUVpBpYvZO5wc/Xb2N11Pva5yXuVUw7eGvcMBAAAAgLtG/E8/Kf7ntVJqatqB1FTF//yz4n76qcDuefToUTVv3lyHDh3SokWLdPjwYc2ZM0fr1q1TcHCwLl26VGD3zs7OnTtVtmxZffnll9q3b58mTJig8ePHa9asWdlet2zZMsXExFhee/fulbOzsx555BFJUmJionbt2qXXXntNu3bt0rJlyxQdHa0HH3wwQ1/z589XTEyMjh07po8++kj/+c9/9MYbbxTI894OwzCUkpJi7zDuOnmaRjpo0CA9/PDDevjhh3X9+nU99dRTlvfpL9wZN1JS9fWOvyRJoa0q2zma3Nl46p8ppBRqAQAAACBzhmHInJiY61fSqVOKmRgm3fp7lsmkmIlhSjp1Ktd95WVjxFGjRsnNzU1r1qxRhw4dVKlSJd17771au3atTp8+rQkTJmjWrFmqX7++5Zrly5fLZDJpzpw5lmNdunTRq6++ann/3XffqWnTpvLw8FDVqlUVHh5uVRAymUz67LPP1Lt3b3l5ealGjRpasWKF5fyQIUP0/vvvq0OHDqpataoef/xxDR48WMuWLcv2efz8/OTv7295/fzzz/Ly8rIU20qUKKGff/5Zffv2Va1atdS6dWvNmjVLO3fu1MmTJ6368vX1lb+/vypWrKgHHnhADz30kHbt2pXr3ErSoEGD1KtXL02fPl0BAQEqVaqURo0apeTkZEubjz76SDVq1JCHh4fKlSunPn36WK7dsGGD3n//fcvgqePHjysiIkImk0k//fSTmjVrJnd3d23atMlyr5s9++yz6tixo+W92WzWtGnTVL16dbm7u6tSpUqaMmWKJKlKlSqSpCZNmshkMlldVxS55LbhwIEDrd4//vjjNg8Gubd631ldvJqkcj7u6lKnrL3DyZFhGPr11K+SpJDyrNcGAAAAAFkxrl1TdNNmNujIkDk+Xke6dM31JbV27ZTJyyvHdpcuXdLq1as1ZcoUeXp6Wp3z9/dXaGiolixZog0bNmjMmDE6f/68ypQpow0bNqh06dKKiIjQU089peTkZG3dulUvv/yyJGnjxo0aMGCAZs6cqZCQEB05ckQjRoyQJIWFhVnuER4ermnTpuntt9/WBx98oNDQUJ04cUJ+fn6ZxnvlypUsz2Vl7ty5evTRR1WsWNYzya5cuSKTySRfX98s2xw8eFC//PKLBg0alKf7S9L69esVEBCg9evX6/Dhw+rXr58aN26s4cOH67ffftOYMWP0n//8R23atNGlS5e0cWPaIJf3339fBw8eVP369TV58mRJUpkyZXT8+HFJ0ssvv6zp06eratWqKlmyZK5iGT9+vD799FO99957ateunWJiYvTnn39KkiIjI9WyZUutXbtW9erVk5ubW56f9W6S62Lb/PnzCzIO5NGX29I2Rni0RSW5ODv+0nsn4k7oVMIpuTi5qHVAa3uHAwAAAAC4DYcOHZJhGKpTp06m5+vUqaO///5bZcuWlZ+fnzZs2KA+ffooIiJCzz//vGUNtcjISCUnJ6tNmzaS0opoL7/8smXAT9WqVfX666/rxRdftCq2DRo0SP3795ckvfnmm5o5c6YiIyPVo0ePDLFs2bJFS5Ys0Y8//pjr54uMjNTevXs1d+7cLNtcv35dL730kvr37y8fHx+rc/3795ezs7NSUlJ048YNPfDAAxo/fnyu75+uZMmSmjVrlpydnVW7dm3df//9WrdunYYPH66TJ0+qWLFieuCBB+Tt7a3KlSurSZMmktJG4bm5ucnLy0v+/v4Z+p08ebK6ds19ETY+Pl7vv/++Zs2aZflsqlWrpnbt2klKK+RJUqlSpTK9X1GT62IbHMehs/GKPHZJzk4m9S8EGyNI/+xC2rxcc3m55vxfSQAAAACgqDJ5eqrWrp25amsYhs6Me0EJv/76z3ptN3N2VvEOHVR++tu5vnde5DTt1N3dXe3bt1dERIS6dOmi/fv3a+TIkZo2bZr+/PNPbdiwQS1atJDX/0bT7d69W5s3b7ZMT5Sk1NRUXb9+XYmJiZZ2DRs2tJwvVqyYfHx8dO7cuQz337t3rx566CGFhYWpW7dukqSTJ0+qbt26ljavvPKKXnnlFavr5s6dqwYNGqhly5aZPldycrL69u0rwzA0e/bsDOffe+89denSRampqTp8+LDGjh2rJ554QosXL87V/dPVq1dPzs7OlvcBAQHas2ePJKlr166qXLmyqlatqh49eqhHjx6WqbU5ad68eY5tbnbgwAHduHFD99xzT56uK6oothVCC7enzQW/p3ZZ+ZfwsHM0uWNZr40ppAAAAACQLZPJlKupnOkC3nhdR3rcK3NCgnRz8ctkklOxYgp4fbKc8tBfblSvXl0mk0kHDhxQ7969M5w/cOCAypQpI19fX3Xs2FGffPKJNm7cqCZNmsjHx8dSgNuwYYM6dOhguS4hIUHh4eGZrgnv4fHP77+urq5W50wmk8xms9Wx/fv365577tGIESOs1oQLDAy02jXz1umlV69e1eLFiy3TL2+VXmg7ceKEfvnllwyj2qS0qbTVq1eXJNWqVUvx8fHq37+/3njjDQUFBWV7/5tl95ze3t7atWuXIiIitGbNGk2cOFGTJk3Sjh07sp3WKinD1FgnJ6cMhdOb14a7daowsuf48w9hJTEpRf/deUqS9HjrwrExQmJyon47+5uktM0RAAAAAAC241KqlALCJ1kX2iTJMBQQPkkupUrZ/J6lSpVS165d9dFHH+natWtW52JjY7Vw4ULLGmUdOnTQ/v37tXTpUsvC+R07dtTatWu1efNmq8X0mzZtqujoaFWvXj3Dy8kp9yWMffv2qVOnTho4cKDVKDlJcnFxser31mLX0qVLdePGjUzXqk8vtB06dEhr165VqVzmNn102rVr13K8f164uLioS5cumjZtmv744w8dP35cv/zyiyTJzc1NqZmNdsxEmTJlFBMTY3Xs5oJgjRo15OnpqXXr1mV6ffoabbm9392OkW2FzPe7zyj+Rooql/JSu+ql7R1OrmyP2a5kc7IqFK+gIJ8ge4cDAAAAAHcd73vvlfdPPyn+l/Vp00mdneXdubN87r23wO45a9YstWnTRt27d9cbb7yhKlWqaN++fXrhhRdUs2ZNTZw4UVLalM+SJUvqq6++0g8//CAprdg2btw4mUwmtW3b1tLnxIkT9cADD6hSpUrq06ePnJyctHv3bu3du1dvvPFGruLau3evOnfurO7du2vs2LGKjY2VlFbwSl9bLDtz585Vr169MhTSkpOT1adPH+3atUs//PCDUlNTLX37+flZbQpw+fJlxcbGymw269ChQ5o8ebJq1qyZ5Rp3+fHDDz/o6NGjat++vUqWLKmVK1fKbDarVq1akqSgoCBt375dx48fV/HixbMt6nXu3Flvv/22vvjiCwUHB+vLL7/U3r17LWvAeXh46KWXXtKLL74oNzc3tW3bVufPn9e+ffs0dOhQlS1bVp6enlq1apUqVKggDw8PlShRwmbPWtgwsq2Q+XJb2hTSx1pWkpOTKYfWjiF9vbaQCiEy3boVNQAAAADgtplMJvlPmmSZLupUrJj8J4XlcNXtqVGjhnbs2KGqVauqb9++qly5su69917VrFlTmzdvVvHixS2xhYSk/T6YvqB+w4YN5ePjo+bNm1tNaezevbt++OEHrVmzRi1atFDr1q313nvvqXLl3M/s+uabb3T+/Hl9+eWXCggIsLxatGiR47XR0dHatGmThg4dmuHc6dOntWLFCp06dUqNGze26nvLli1WbQcPHqyAgABVqFBB/fv3V7169fTTTz/JxcV2Y558fX21bNkyde7cWXXq1NGcOXO0aNEi1atXT5I0btw4OTs7q27duipTpoxOnjyZZV/du3fXa6+9phdffFEtWrRQfHy8BgwYYNXmtdde0/PPP6+JEyeqTp066tevn2WdPBcXF82cOVMff/yxAgMD9dBDD9nsOQsjRrYVIn+cuqw9p6/IzdlJfZpVsHc4uWIYxj/FNtZrAwAAAIAC41KqlAImhyt2ypvyf3VCgUwfvVVQUJAWLFhgeR8WFqZ3331Xf/zxh1q3bm05vnz5cqvrnJycdOnSpUz77N69u7p3757lPTPblOHy5cuWP0+aNEmTJk3KVfy3qlWrVpabPgQFBeW4IURW8eXGrXHfnNd0M2bMsPy5Xbt2ioiIyLK/mjVrauvWrVbHsnuG8PBwhYeHZ9mfk5OTJkyYoAkTJmR6ftiwYRo2bFiW1xclFNsKkS+3nZAk3dfAX6WKu9s5mtw5dPmQYq/Gyt3ZXS38c/6vCAAAAACA/PO5994CnTqak/DwcAUFBWnbtm1q2bJlntZZA+4WFNsKiSvXkrVi9xlJUmgh2RhB+mcX0pb+LeXhUjh2TgUAAAAA5N/gwYPtHQJgV5SYC4llu07perJZtcp5q3nlkvYOJ9duXq8NAAAAAADgbkexrRAwDEMLt6ctZBjaulKh2WQgLilOUeeiJEntyrezbzAAAAAAAAB3AMW2QiDy+N86fC5BXm7O6t2kvL3DybWtZ7Yq1UhVlRJVVNG7or3DAQAAAACHld9F9QHcObn9e0qxrRBYtOOUJOmhxoHy9nC1czS5l75eG7uQAgAAAEDmXF3TfsdLTEy0cyQAcpL+9zT9721W2CDBwcUlSWv2n5UkhbYqPBsjmA2zNp3eJIn12gAAAAAgK87OzvL19dW5c+ckSV5eXoVm6SCgqDAMQ4mJiTp37px8fX3l7OycbXuKbQ5u+3mTklMNNaroq/rlS9g7nFw7cOmALl6/KC8XLzUr28ze4QAAAACAw/L395ckS8ENgGPy9fW1/H3NDsU2B5VqNrTlyEWtP5M20/exloVrzbP0KaTBgcFydS48U18BAAAA4E4zmUwKCAhQ2bJllZycbO9wAGTC1dU1xxFt6Si2OaBVe2MU/v1+xVy5Lilt+PB7Px9UCU9X9agfYN/gcmnjadZrAwAAAIC8cHZ2zvUv8wAcFxskOJhVe2P09Je7/ldo+8fZuBt6+stdWrU3xk6R5d7f1//WnvN7JEntyrezczQAAAAAAAB3DsU2B5JqNhT+/X5ltpFs+rHw7/cr1ezYW0JvPrNZhgzVKllL5YqVs3c4AAAAAAAAdwzFNgcSeexShhFtNzMkxVy5rshjl+5cUPmQvl4bu5ACAAAAAICihmKbAzkXn3WhLT/t7CHVnKrNZzZLYr02AAAAAABQ9FBscyBlvT1s2s4e9lzYoys3rsjbzVsNyzS0dzgAAAAAAAB3FMU2B9Kyip8CSnj8b//RjEySAkp4qGUVvzsZVp6k70LaNrCtXJzY7BYAAAAAABQtFNsciLOTSWE960pShoJb+vuwnnXl7JRVOc7+WK8NAAAAAAAUZRTbHEyP+gGa/XhT+ZewnirqX8JDsx9vqh71A+wUWc7OJ57XgUsHJKWNbAMAAAAAAChqmOfngHrUD1DXuv7aevic1mzcrm4hrRRcvaxDj2iTpE2nN0mS6peqr1KepewcDQAAAAAAwJ1Hsc1BOTuZ1KqKny4eMNSqip/DF9qkf9ZrYwopAAAAAAAoqphGCptINidry5ktkqSQ8hTbAAAAAABA0USxDTYRdS5KV5Ovys/DT/VK17N3OAAAAAAAAHZBsQ02kb4LadvAtnIy8bUCAAAAAABFE1UR2ATrtQEAAAAAAFBsgw2cSTijw5cPy8nkpDaBbewdDgAAAAAAgN1QbMNt23R6kySpUZlGKuFews7RAAAAAAAA2A/FNty29PXa2ldob+dIAAAAAAAA7ItiG27LjdQb2h67XZIUUp712gAAAAAAQNFGsQ23ZWfsTl1LuaaynmVVs2RNe4cDAAAAAABgVxTbcFtu3oXUZDLZORoAAAAAAAD7otiG22IptjGFFAAAAAAAgGIb8u9E3AmdiDshFycXtQpoZe9wAAAAAAAA7I5iG/Jt0+lNkqRmZZupuFtxO0cDAAAAAABgfxTbkG8bT/2zXhsAAAAAAAAotiGfEpMTtSN2hyTWawMAAAAAAEhHsQ35siN2h5LMSSpfvLyqlKhi73AAAAAAAAAcAsU25Ev6LqTtyreTyWSyczQAAAAAAACOgWIb8swwDMt6be0rtLdzNAAAAAAAAI7DIYptH374oYKCguTh4aFWrVopMjIyy7YLFiyQyWSyenl4eNzBaHHk8hGduXpGbk5uauHfwt7hAAAAAAAAOAy7F9uWLFmisWPHKiwsTLt27VKjRo3UvXt3nTt3LstrfHx8FBMTY3mdOHHiDkaM9CmkLQJayNPF087RAAAAAAAAOA67F9veffddDR8+XIMHD1bdunU1Z84ceXl5ad68eVleYzKZ5O/vb3mVK1fuDkaM9GIbu5ACAAAAAABYc7HnzZOSkrRz506NHz/ecszJyUldunTR1q1bs7wuISFBlStXltlsVtOmTfXmm2+qXr16mba9ceOGbty4YXkfFxcnSUpOTlZycrKNnqRgpMfnSHHGJ8Xr97O/S5Jal2vtULHlxBHzWdiRU9sin7ZHTm2LfNoeObUt8ml75NS2yKftFZacOnp8AGzLZBiGYa+bnzlzRuXLl9eWLVsUHBxsOf7iiy9qw4YN2r59e4Zrtm7dqkOHDqlhw4a6cuWKpk+frl9//VX79u1ThQoVMrSfNGmSwsPDMxz/6quv5OXlZdsHKgL2Je3TosRFKu1UWs/6PGvvcAAAAADA4SUmJuqxxx7TlStX5OPjY+9wABQwu45sy4/g4GCrwlybNm1Up04dffzxx3r99dcztB8/frzGjh1reR8XF6eKFSuqW7duDv+PXHJysn7++Wd17dpVrq6u9g5HkrRj2w7pqNStRjfd1+w+e4eTJ46Yz8KOnNoW+bQ9cmpb5NP2yKltkU/bI6e2RT5tr7DkNH2GFYCiwa7FttKlS8vZ2Vlnz561On727Fn5+/vnqg9XV1c1adJEhw8fzvS8u7u73N3dM73Okf8xvpmjxGoYhjbHbJYkdajUwSFiyg9HyefdhJzaFvm0PXJqW+TT9sipbZFP2yOntkU+bc/Rc+rIsQGwPbtukODm5qZmzZpp3bp1lmNms1nr1q2zGr2WndTUVO3Zs0cBAQEFFSb+589Lf+rCtQvydPFU83LN7R0OAAAAAACAw7H7NNKxY8dq4MCBat68uVq2bKkZM2bo6tWrGjx4sCRpwIABKl++vKZOnSpJmjx5slq3bq3q1avr8uXLevvtt3XixAkNGzbMno9RJKTvQto6oLXcnN3sHA0AAAAAAIDjsXuxrV+/fjp//rwmTpyo2NhYNW7cWKtWrVK5cuUkSSdPnpST0z8D8P7++28NHz5csbGxKlmypJo1a6YtW7aobt269nqEImPjqbRiW0iFEDtHAgAAAAAA4JjsXmyTpNGjR2v06NGZnouIiLB6/9577+m99967A1HhZpevX9YfF/6QJIWUp9gGAAAAAACQGbuu2YbCY8uZLTIbZtUoWUP+xXK3eQUAAAAAAEBRQ7ENuZK+Xhuj2gAAAAAAALJGsQ05SjWnavPpzZIotgEAAAAAAGSHYhtytO/iPv194295u3qrUdlG9g4HAAAAAADAYVFsQ47Sp5AGBwbL1cnVztEAAAAAAAA4LoptyNHGU/9br60CU0gBAAAAAACyQ7EN2bpw7YL2XdwnSWpXvp2dowEAAAAAAHBsFNuQrfSNEeqWqqvSnqXtHA0AAAAAAIBjo9iGbP166ldJ7EIKAAAAAACQGxTbkKVkc7K2ntkqifXaAAAAAAAAcoNiG7K0+9xuxSfHy9fdV/VL1bd3OAAAAAAAAA6PYhuytPF02i6kbcu3lbOTs52jAQAAAAAAcHwU25Cl9GIb67UBAAAAAADkDsU2ZCr2aqwO/X1ITiYntQ1sa+9wAAAAAAAACgWKbchU+qi2hqUbytfD177BAAAAAAAAFBIU25Cpjaf+N4WUXUgBAAAAAAByjWIbMkhKTdK2mG2SWK8NAAAAAAAgLyi2IYOdZ3fqWso1lfEso9p+te0dDgAAAAAAQKFBsQ0ZpK/X1q58O5lMJjtHAwAAAAAAUHhQbEMGrNcGAAAAAACQPxTbYOWvuL90PO64XEwuah3Q2t7hAAAAAAAAFCoU22AlfQppk3JN5O3mbedoAAAAAAAACheKbbCSXmxjF1IAAAAAAIC8o9gGi2sp17Qjdockim0AAAAAAAD5QbENFjtid+hG6g0FFAtQNd9q9g4HAAAAAACg0KHYBgvLLqTlQ2QymewcDQAAAAAAQOFDsQ2SJMMw/lmvrQJTSAEAAAAAAPKDYhskSceuHNPphNNydXJVS/+W9g4HAAAAAACgUKLYBkn/7ELawr+FvFy97BwNAAAAAABA4USxDZKs12sDAAAAAABA/lBsgxKSErTz3E5JrNcGAAAAAABwOyi2QdtjtivFnKJK3pVU2aeyvcMBAAAAAAAotCi2gV1IAQAAAAAAbIRiWxFnGIZlvbb25dvbORoAAAAAAIDCjWJbEXfw74M6d+2cPF081cy/mb3DAQAAAAAAKNQothVx6VNIW/m3kruzu52jAQAAAAAAKNwothVx6VNIWa8NAAAAAADg9lFsK8Ku3LiiqPNRkqR25dvZNxgAAAAAAIC7AMW2Imzrma0yG2ZV962uwOKB9g4HAAAAAACg0KPYVoSlr9cWUp4ppAAAAAAAALZAsa2IMhtmbTq9SRLrtQEAAAAAANgKxbYiav/F/bp0/ZKKuRZT47KN7R0OAAAAAADAXYFiWxGVvgtpm8A2cnVytXM0AAAAAAAAdweKbUUU67UBAAAAAADYHsW2IujitYvae2GvJKlt+bZ2jgYAAAAAAODuQbGtCNpyZosMGarjV0dlvcraOxwAAAAAAIC7BsW2IujXU79KktqVb2fnSAAAAAAAAO4uFNuKmBRzijaf2SxJal+hvZ2jAQAAAAAAuLtQbCti/jj/h+KT4lXCvYQalG5g73AAAAAAAADuKhTbipj0XUjbBLaRs5OznaMBAAAAAAC4u1BsK2I2nkortoWUD7FzJAAAAAAAAHcfim1FyNmrZxX9d7RMMrE5AgAAAAAAQAGg2FaEbDq9SZLUoEwDlfQoaedoAAAAAAAA7j4U24qQ9PXamEIKAAAAAABQMCi2FRHJqcnaemarJCmkAsU2AAAAAACAgkCxrYjYdW6XElMSVcqjlOr41bF3OAAAAAAAAHclim1FRPoupO3Kt5OTiY8dAAAAAACgIFB1KSIs67UxhRQAAAAAAKDAUGwrAk7Fn9LRK0flbHJWcGCwvcMBAAAAAAC4a1FsKwI2nd4kSWpctrF83HzsHA0AAAAAAMDdi2JbEWCZQlqeKaQAAAAAAAAFiWLbXe56ynVFxkRKYr02AAAAAACAgkax7S7329nfdD31usp5lVMN3xr2DgcAAAAAAOCuRrHtLrfx1D+7kJpMJjtHAwAAAAAAcHej2HYXMwxDv576VRLrtQEAAAAAANwJFNvuYsfjjutUwim5OLmodUBre4cDAAAAAABw16PYdhdLn0LavFxzebl62TkaAAAAAACAux/FtrvYxtP/W6+NKaQAAAAAAAB3BMW2u1RicqJ+O/ubpLTNEQAAAAAAAFDwKLbdpbbFbFOKOUUVildQkE+QvcMBAAAAAAAoEii23aXSp5C2r9BeJpPJztEAAAAAAAAUDRTb7kKGYVg2R2AKKQAAAAAAwJ3jEMW2Dz/8UEFBQfLw8FCrVq0UGRmZq+sWL14sk8mkXr16FWyAhcyhy4d0NvGsPJw91Lxcc3uHAwAAAAAAUGTYvdi2ZMkSjR07VmFhYdq1a5caNWqk7t2769y5c9led/z4cY0bN04hIYzculX6qLaWAS3l4eJh52gAAAAAAACKDrsX2959910NHz5cgwcPVt26dTVnzhx5eXlp3rx5WV6Tmpqq0NBQhYeHq2rVqncw2sIhfb22kPIUIgEAAAAAAO4kF3vePCkpSTt37tT48eMtx5ycnNSlSxdt3bo1y+smT56ssmXLaujQodq4cWO297hx44Zu3LhheR8XFydJSk5OVnJy8m0+QcFKjy8vccYnxSvqXJQkqXW51g7/jHdSfvKJ7JFT2yKftkdObYt82h45tS3yaXvk1LbIp+0Vlpw6enwAbMtkGIZhr5ufOXNG5cuX15YtWxQcHGw5/uKLL2rDhg3avn17hms2bdqkRx99VFFRUSpdurQGDRqky5cva/ny5ZneY9KkSQoPD89w/KuvvpKXl5fNnsVR7E3aq8WJi1XGqYye8XnG3uEAAAAAQJGXmJioxx57TFeuXJGPj4+9wwFQwOw6si2v4uPj9cQTT+jTTz9V6dKlc3XN+PHjNXbsWMv7uLg4VaxYUd26dXP4f+SSk5P1888/q2vXrnJ1dc3VNdu3bZeOSj1q9tB9Te8r4AgLl/zkE9kjp7ZFPm2PnNoW+bQ9cmpb5NP2yKltkU/bKyw5TZ9hBaBosGuxrXTp0nJ2dtbZs2etjp89e1b+/v4Z2h85ckTHjx9Xz549LcfMZrMkycXFRdHR0apWrZrVNe7u7nJ3d8/Ql6urq0P/Y3yz3MZqNszacmaLJKlDpQ6F5vnutML02RcW5NS2yKftkVPbIp+2R05ti3zaHjm1LfJpe46eU0eODYDt2XWDBDc3NzVr1kzr1q2zHDObzVq3bp3VtNJ0tWvX1p49exQVFWV5Pfjgg+rUqZOioqJUsWLFOxm+wzlw6YAuXr8oLxcvNS3b1N7hAAAAAAAAFDl2n0Y6duxYDRw4UM2bN1fLli01Y8YMXb16VYMHD5YkDRgwQOXLl9fUqVPl4eGh+vXrW13v6+srSRmOF0UbT6VtFhEcGCxXZ/7LCQAAAAAAwJ1m92Jbv379dP78eU2cOFGxsbFq3LixVq1apXLlykmSTp48KScnuw7AKzQ2nk4rtoWUD7FzJAAAAAAAAEWT3YttkjR69GiNHj0603MRERHZXrtgwQLbB1QI/X39b+05v0eS1K58OztHAwAAAAAAUDQxZOwusfnMZhkyVKtkLZUrVs7e4QAAAAAAABRJFNvuEr+e+lWSFFKBKaQAAAAAAAD2QrHtLpBqTtXm05slsV4bAAAAAACAPVFsuwvsubBHcUlx8nbzVsMyDe0dDgAAAAAAQJFFse0ukD6FtG1gW7k4OcSeFwAAAAAAAEUSxba7wKbTmySxXhsAAAAAAIC9UWwr5M4lntOBSwdkkkltA9vaOxwAAAAAAIAijWJbIZe+MUL90vVVyrOUnaMBAAAAAAAo2ii2FXIbT2+UxC6kAAAAAAAAjoBiWyGWbE7WljNbJLFeGwAAAAAAgCOg2FaIRZ2L0tXkq/Lz8FPdUnXtHQ4AAAAAAECRR7GtENt4Km0Kabvy7eRk4qMEAAAAAACwNyo0hRjrtQEAAAAAADgWim2F1JmEMzp8+bCcTE4KDgy2dzgAAAAAAAAQxbZCa9PpTZKkxmUaq4R7CTtHAwAAAAAAAIliW6GVvl4bu5ACAAAAAAA4DopthdCN1BvaHrtdEuu1AQAAAAAAOBKKbYXQztidupZyTWU9y6pmyZr2DgcAAAAAAAD/Q7GtELLsQlohRCaTyc7RAAAAAAAAIB3FtkLIUmxjCikAAAAAAIBDodhWyJyIO6ETcSfk4uSiVgGt7B0OAAAAAAAAbkKxrZBJ34W0WdlmKu5W3M7RAAAAAAAA4GYU2wqZm9drAwAAAAAAgGOh2FaIJCYnakfsDkms1wYAAAAAAOCIKLYVIpGxkUo2J6t88fKqUqKKvcMBAAAAAADALSi2FSLp67WFlA+RyWSyczQAAAAAAAC4FcW2QsIwDNZrAwAAAAAAcHAU2wqJI5ePKOZqjNyd3dXCv4W9wwEAAAAAAEAmKLYVEumj2lr4t5Cni6edowEAAAAAAEBmKLYVEpYppOxCCgAAAAAA4LAothUC8Unx+v3s75JYrw0AAAAAAMCRUWwrBCJjI5VipCjIJ0gVvSvaOxwAAAAAAABkgWJbIbDpzCZJjGoDAAAAAABwdBTbHJxhGNp8ZrMk1msDAAAAAABwdBTbHFxMaowuXL8gTxdPNSvXzN7hAAAAAAAAIBsU2xzcwZSDkqTWAa3l5uxm52gAAAAAAACQHYptDu5gclqxjfXaAAAAAAAAHB/FNgd2+cZl/ZX6lyTWawMAAAAAACgMKLY5sG0x22TIUHXf6vIv5m/vcAAAAAAAAJADim0ObPmR5ZKkqj5V7RsIAAAAAAAAcoVim4NKSU3RznM7JUkH/z4owzDsHBEAAAAAAAByQrHNQS2KXqRUI1WSdDz+uLac2WLniAAAAAAAAJATim0OyDAMzd873/LeyeSkD37/gNFtAAAAAAAADo5imwPacmaLzl87b3lvNszad3Efo9sAAAAAAAAcHMU2B2MYhj74/QM5maw/Gka3AQAAAAAAOD6KbQ5my5kt2ndxn8yG2eo4o9sAAAAAAAAcH8U2B5I+qs0kU6bnTTIxug0AAAAAAMCBUWxzIMnmZMVejZWhzItphgzFXo1Vsjn5DkcGAAAAAACA3HCxdwD4h5uzmxY/sFiXrl+SJKWkpGjzps1q266tXFzSPio/Dz+5ObvZM0wAAAAAAABkgWKbg/Ev5i//Yv6SpOTkZB1zOaY6fnXk6upq58gAAAAAAACQE6aRAgAAAAAAADZCsQ0AAAAAAACwEYptAAAAAAAAgI1QbAMAAAAAAABshGIbAAAAAAAAYCMU2wAAAAAAAAAbodgGAAAAAAAA2AjFNgAAAAAAAMBGKLYBAAAAAAAANkKxDQAAAAAAALARim0AAAAAAACAjbjYO4A7zTAMSVJcXJydI8lZcnKyEhMTFRcXJ1dXV3uHU+iRT9sjp7ZFPm2PnNoW+bQ9cmpb5NP2yKltkU/bKyw5Tf/9M/33UQB3tyJXbIuPj5ckVaxY0c6RAAAAAACKkvj4eJUoUcLeYQAoYCajiJXWzWazzpw5I29vb5lMJnuHk624uDhVrFhRf/31l3x8fOwdTqFHPm2PnNoW+bQ9cmpb5NP2yKltkU/bI6e2RT5tr7Dk1DAMxcfHKzAwUE5OrOYE3O2K3Mg2JycnVahQwd5h5ImPj49D/+AobMin7ZFT2yKftkdObYt82h45tS3yaXvk1LbIp+0Vhpwyog0oOiipAwAAAAAAADZCsQ0AAAAAAACwEYptDszd3V1hYWFyd3e3dyh3BfJpe+TUtsin7ZFT2yKftkdObYt82h45tS3yaXvkFIAjKnIbJAAAAAAAAAAFhZFtAAAAAAAAgI1QbAMAAAAAAABshGIbAAAAAAAAYCMU2wAAAAAAAAAbodhmRx9++KGCgoLk4eGhVq1aKTIyMtv2S5cuVe3ateXh4aEGDRpo5cqVdyjSwiMvOf30008VEhKikiVLqmTJkurSpUuOn0FRlNfvabrFixfLZDKpV69eBRtgIZPXfF6+fFmjRo1SQECA3N3dVbNmTf7u3yKvOZ0xY4Zq1aolT09PVaxYUc8995yuX79+h6J1bL/++qt69uypwMBAmUwmLV++PMdrIiIi1LRpU7m7u6t69epasGBBgcdZWOQ1n8uWLVPXrl1VpkwZ+fj4KDg4WKtXr74zwRYS+fmOptu8ebNcXFzUuHHjAouvsMlPPm/cuKEJEyaocuXKcnd3V1BQkObNm1fwwRYS+cnpwoUL1ahRI3l5eSkgIEBDhgzRxYsXCz7YQmDq1Klq0aKFvL29VbZsWfXq1UvR0dE5XsfvTQDsjWKbnSxZskRjx45VWFiYdu3apUaNGql79+46d+5cpu23bNmi/v37a+jQofr999/Vq1cv9erVS3v37r3DkTuuvOY0IiJC/fv31/r167V161ZVrFhR3bp10+nTp+9w5I4rrzlNd/z4cY0bN04hISF3KNLCIa/5TEpKUteuXXX8+HF98803io6O1qeffqry5cvf4cgdV15z+tVXX+nll19WWFiYDhw4oLlz52rJkiV65ZVX7nDkjunq1atq1KiRPvzww1y1P3bsmO6//3516tRJUVFRevbZZzVs2DAKRP+T13z++uuv6tq1q1auXKmdO3eqU6dO6tmzp37//fcCjrTwyGtO012+fFkDBgzQPffcU0CRFU75yWffvn21bt06zZ07V9HR0Vq0aJFq1apVgFEWLnnN6ebNmzVgwAANHTpU+/bt09KlSxUZGanhw4cXcKSFw4YNGzRq1Cht27ZNP//8s5KTk9WtWzddvXo1y2v4vQmAQzBgFy1btjRGjRpleZ+ammoEBgYaU6dOzbR93759jfvvv9/qWKtWrYwnn3yyQOMsTPKa01ulpKQY3t7exueff15QIRY6+clpSkqK0aZNG+Ozzz4zBg4caDz00EN3INLCIa/5nD17tlG1alUjKSnpToVY6OQ1p6NGjTI6d+5sdWzs2LFG27ZtCzTOwkiS8e2332bb5sUXXzTq1atndaxfv35G9+7dCzCywik3+cxM3bp1jfDwcNsHdBfIS0779etnvPrqq0ZYWJjRqFGjAo2rsMpNPn/66SejRIkSxsWLF+9MUIVcbnL69ttvG1WrVrU6NnPmTKN8+fIFGFnhde7cOUOSsWHDhizb8HsTAEfAyDY7SEpK0s6dO9WlSxfLMScnJ3Xp0kVbt27N9JqtW7datZek7t27Z9m+qMlPTm+VmJio5ORk+fn5FVSYhUp+czp58mSVLVtWQ4cOvRNhFhr5yeeKFSsUHBysUaNGqVy5cqpfv77efPNNpaam3qmwHVp+ctqmTRvt3LnTMtX06NGjWrlype677747EvPdhp9NBctsNis+Pp6fS7dp/vz5Onr0qMLCwuwdSqG3YsUKNW/eXNOmTVP58uVVs2ZNjRs3TteuXbN3aIVWcHCw/vrrL61cuVKGYejs2bP65ptv+LmUhStXrkhStv8u8rMJgCNwsXcARdGFCxeUmpqqcuXKWR0vV66c/vzzz0yviY2NzbR9bGxsgcVZmOQnp7d66aWXFBgYmOGHc1GVn5xu2rRJc+fOVVRU1B2IsHDJTz6PHj2qX375RaGhoVq5cqUOHz6skSNHKjk5mV8alb+cPvbYY7pw4YLatWsnwzCUkpKip556immk+ZTVz6a4uDhdu3ZNnp6edors7jB9+nQlJCSob9++9g6l0Dp06JBefvllbdy4US4u/N/e23X06FFt2rRJHh4e+vbbb3XhwgWNHDlSFy9e1Pz58+0dXqHUtm1bLVy4UP369dP169eVkpKinj175nmqdFFgNpv17LPPqm3btqpfv36W7fi9CYAjYGQbIOnf//63Fi9erG+//VYeHh72DqdQio+P1xNPPKFPP/1UpUuXtnc4dwWz2ayyZcvqk08+UbNmzdSvXz9NmDBBc+bMsXdohVZERITefPNNffTRR9q1a5eWLVumH3/8Ua+//rq9QwOsfPXVVwoPD9fXX3+tsmXL2jucQik1NVWPPfaYwsPDVbNmTXuHc1cwm80ymUxauHChWrZsqfvuu0/vvvuuPv/8c0a35dP+/fv1zDPPaOLEidq5c6dWrVql48eP66mnnrJ3aA5n1KhR2rt3rxYvXmzvUAAgR/wnPjsoXbq0nJ2ddfbsWavjZ8+elb+/f6bX+Pv756l9UZOfnKabPn26/v3vf2vt2rVq2LBhQYZZqOQ1p0eOHNHx48fVs2dPyzGz2SxJcnFxUXR0tKpVq1awQTuw/HxHAwIC5OrqKmdnZ8uxOnXqKDY2VklJSXJzcyvQmB1dfnL62muv6YknntCwYcMkSQ0aNNDVq1c1YsQITZgwQU5O/DeovMjqZ5OPjw+j2m7D4sWLNWzYMC1dupTR1rchPj5ev/32m37//XeNHj1aUtrPJcMw5OLiojVr1qhz5852jrJwCQgIUPny5VWiRAnLsTp16sgwDJ06dUo1atSwY3SF09SpU9W2bVu98MILkqSGDRuqWLFiCgkJ0RtvvKGAgAA7R+gYRo8erR9++EG//vqrKlSokG1bfm8C4Aj4rcIO3Nzc1KxZM61bt85yzGw2a926dQoODs70muDgYKv2kvTzzz9n2b6oyU9OJWnatGl6/fXXtWrVKjVv3vxOhFpo5DWntWvX1p49exQVFWV5Pfjgg5ZdCitWrHgnw3c4+fmOtm3bVocPH7YULSXp4MGDCggIKPKFNil/OU1MTMxQUEsvZhqGUXDB3qX42WR7ixYt0uDBg7Vo0SLdf//99g6nUPPx8cnwc+mpp55SrVq1FBUVpVatWtk7xEKnbdu2OnPmjBISEizHDh48KCcnpxwLIMgcP5eyZxiGRo8erW+//Va//PKLqlSpkuM1/GwC4BDsuDlDkbZ48WLD3d3dWLBggbF//35jxIgRhq+vrxEbG2sYhmE88cQTxssvv2xpv3nzZsPFxcWYPn26ceDAASMsLMxwdXU19uzZY69HcDh5zem///1vw83Nzfjmm2+MmJgYyys+Pt5ej+Bw8prTW7EbqbW85vPkyZOGt7e3MXr0aCM6Otr44YcfjLJlyxpvvPGGvR7B4eQ1p2FhYYa3t7exaNEi4+jRo8aaNWuMatWqGX379rXXIziU+Ph44/fffzd+//13Q5Lx7rvvGr///rtx4sQJwzAM4+WXXzaeeOIJS/ujR48aXl5exgsvvGAcOHDA+PDDDw1nZ2dj1apV9noEh5LXfC5cuNBwcXExPvzwQ6ufS5cvX7bXIzicvOb0VuxGai2v+YyPjzcqVKhg9OnTx9i3b5+xYcMGo0aNGsawYcPs9QgOJ685nT9/vuHi4mJ89NFHxpEjR4xNmzYZzZs3N1q2bGmvR3AoTz/9tFGiRAkjIiLC6t/FxMRESxt+bwLgiCi22dEHH3xgVKpUyXBzczNatmxpbNu2zXKuQ4cOxsCBA63af/3110bNmjUNNzc3o169esaPP/54hyN2fHnJaeXKlQ1JGV5hYWF3PnAHltfv6c0otmWU13xu2bLFaNWqleHu7m5UrVrVmDJlipGSknKHo3ZseclpcnKyMWnSJKNatWqGh4eHUbFiRWPkyJHG33//fecDd0Dr16/P9N/F9BwOHDjQ6NChQ4ZrGjdubLi5uRlVq1Y15s+ff8fjdlR5zWeHDh2ybY/8fUdvRrHNWn7yeeDAAaNLly6Gp6enUaFCBWPs2LFWhY+iLj85nTlzplG3bl3D09PTCAgIMEJDQ41Tp07d+eAdUGa5lGT1s4bfmwA4IpNhMD4ZAAAAAAAAsAXWbAMAAAAAAABshGIbAAAAAAAAYCMU2wAAAAAAAAAbodgGAAAAAAAA2AjFNgAAAAAAAMBGKLYBAAAAAAAANkKxDQAAAAAAALARim0AAAAAAACAjVBsAwBYmEwmLV++PM/XRUdHy9/fX/Hx8TaNZ9CgQerVq5dN+yxMjh8/LpPJpKioqFxf07FjRz377LMFFlNhkZiYqH/961/y8fGRyWTS5cuXFRQUpBkzZtg7tDtuwYIF8vX1tXcYkgr+O/3oo4/qnXfeyV9wAAAANkKxDQAcwKBBg2QymTK8evToYe/QcmX8+PH6v//7P3l7e1uO/fHHHwoJCZGHh4cqVqyoadOm2TFCZOfSpUsKDQ2Vj4+PfH19NXToUCUkJGTb/v/+7/9Uq1YteXp6qlKlShozZoyuXLly27F8+umnCgkJUcmSJVWyZEl16dJFkZGRee7n888/18aNG7VlyxbFxMSoRIkS2rFjh0aMGHHbMeakqBb1HMGrr76qKVOm2OS7CAAAkF8U2wDAQfTo0UMxMTFWr0WLFtk7rBydPHlSP/zwgwYNGmQ5FhcXp27duqly5crauXOn3n77bU2aNEmffPKJ/QJFlkJDQ7Vv3z79/PPP+uGHH/Trr79mW5Q6c+aMzpw5o+nTp2vv3r1asGCBVq1apaFDh952LBEREerfv7/Wr1+vrVu3qmLFiurWrZtOnz6dp36OHDmiOnXqqH79+vL395fJZFKZMmXk5eV12zHCcdWvX1/VqlXTl19+ae9QAABAEUaxDQAchLu7u/z9/a1eJUuWtJw3mUyaPXu27r33Xnl6eqpq1ar65ptvrPrYs2ePOnfuLE9PT5UqVUojRozIMEJp3rx5qlevntzd3RUQEKDRo0dbnb9w4YJ69+4tLy8v1ahRQytWrMg27q+//lqNGjVS+fLlLccWLlyopKQky70effRRjRkzRu+++26+chMeHq4yZcrIx8dHTz31lJKSkiznVq1apXbt2snX11elSpXSAw88oCNHjljOJyUlafTo0QoICJCHh4cqV66sqVOnWs5fvnxZw4YNs/TfuXNn7d69O8tY0qfBff311woJCZGnp6datGihgwcPaseOHWrevLmKFy+ue++9V+fPn7dcZzabNXnyZFWoUEHu7u5q3LixVq1aZdV3ZGSkmjRpIg8PDzVv3ly///57hvvv3btX9957r4oXL65y5crpiSee0IULF/KVV0k6cOCAVq1apc8++0ytWrVSu3bt9MEHH2jx4sU6c+ZMptfUr19f//3vf9WzZ09Vq1ZNnTt31pQpU/T9998rJSUl37FIad+dkSNHqnHjxqpdu7Y+++wzmc1mrVu3Ltd9dOzYUe+8845+/fVXmUwmdezYUVLGEWcmk0mfffZZtt/3vOa7Y8eOOnHihJ577jnLCFVJmjRpkho3bmzVdsaMGQoKCrK8T582PX36dAUEBKhUqVIaNWqUkpOTLW1u3LihcePGqXz58ipWrJhatWqliIgIq34XLFigSpUqycvLS71799bFixezzVdh+05/9NFHqlGjhjw8PFSuXDn16dPH6nzPnj21ePHibJ8ZAACgIFFsA4BC5LXXXtO//vUv7d69W6GhoXr00Ud14MABSdLVq1fVvXt3lSxZUjt27NDSpUu1du1aq2La7NmzNWrUKI0YMUJ79uzRihUrVL16dat7hIeHq2/fvvrjjz903333KTQ0VJcuXcoypo0bN6p58+ZWx7Zu3ar27dvLzc3Ncqx79+6Kjo7W33//LSltBJPJZNLx48ezfeZ169bpwIEDioiI0KJFi7Rs2TKFh4dbzl+9elVjx47Vb7/9pnXr1snJyUm9e/eW2WyWJM2cOVMrVqzQ119/rejoaC1cuNCqwPHII4/o3Llz+umnn7Rz5041bdpU99xzT7bPLElhYWF69dVXtWvXLrm4uOixxx7Tiy++qPfff18bN27U4cOHNXHiREv7999/X++8846mT5+uP/74Q927d9eDDz6oQ4cOSZISEhL0wAMPqG7dutq5c6cmTZqkcePGWd3z8uXL6ty5s5o0aaLffvtNq1at0tmzZ9W3b99sY83O1q1b5evra/UZdunSRU5OTtq+fXuu+7ly5Yp8fHzk4uKS71gyk5iYqOTkZPn5+VmOTZo0yeozvNWyZcs0fPhwBQcHKyYmRsuWLcuybXbf9/zke9myZapQoYImT55sGaGaF+vXr9eRI0e0fv16ff7551qwYIEWLFhgOT969Ght3bpVixcv1h9//KFHHnlEPXr0sHyPtm/frqFDh2r06NGKiopSp06d9MYbb+Tq3oXhO/3bb79pzJgxmjx5sqKjo7Vq1Sq1b9/eqk3Lli0VGRmpGzdu5Oq5AQAAbM4AANjdwIEDDWdnZ6NYsWJWrylTpljaSDKeeuopq+tatWplPP3004ZhGMYnn3xilCxZ0khISLCc//HHHw0nJycjNjbWMAzDCAwMNCZMmJBlHJKMV1991fI+ISHBkGT89NNPWV7TqFEjY/LkyVbHunbtaowYMcLq2L59+wxJxv79+w3DMIzt27cbtWrVMk6dOpVl3wMHDjT8/PyMq1evWo7Nnj3bKF68uJGamprpNefPnzckGXv27DEMwzD+7//+z+jcubNhNpsztN24caPh4+NjXL9+3ep4tWrVjI8//jjT/o8dO2ZIMj777DPLsUWLFhmSjHXr1lmOTZ061ahVq5blfWBgoNXnaRiG0aJFC2PkyJGGYRjGxx9/bJQqVcq4du2a1bNKMn7//XfDMAzj9ddfN7p162bVx19//WVIMqKjow3DMIwOHToYzzzzTKaxZ2bKlClGzZo1MxwvU6aM8dFHH+Wqj/PnzxuVKlUyXnnllVzfN7eefvppo2rVqlZ5+eCDD4zOnTtne90zzzxjdOjQwepY5cqVjffee8/yPqfve27ynZlb72MYhhEWFmY0atTI6th7771nVK5c2fJ+4MCBRuXKlY2UlBTLsUceecTo16+fYRiGceLECcPZ2dk4ffq0VT/33HOPMX78eMMwDKN///7GfffdZ3W+X79+RokSJbKMtzB9p//73/8aPj4+RlxcXJbPs3v3bkOScfz48SzbAAAAFCRGtgGAg+jUqZOioqKsXk899ZRVm+Dg4Azv00e2HThwQI0aNVKxYsUs59u2bSuz2azo6GidO3dOZ86c0T333JNtHA0bNrT8uVixYvLx8dG5c+eybH/t2jV5eHjk+jnTtWzZUn/++afV9NPMNGrUyGqdreDgYCUkJOivv/6SJB06dEj9+/dX1apV5ePjYxnxdPLkSUlpU/OioqJUq1YtjRkzRmvWrLH0tXv3biUkJKhUqVIqXry45XXs2DGrqaiZuTlP5cqVkyQ1aNDA6lh63uLi4nTmzBm1bdvWqo+2bdtaYeGwggAACM1JREFUfX4NGza0yuWtn/fu3bu1fv16q1hr164tSTnGW1Di4uJ0//33q27dupo0aVKW7d58802ruNM/n+z8+9//1uLFi/Xtt99a5WX06NF5mlaaney+7znle+HChVbnNm7ceNvx1KtXT87Ozpb3AQEBlnj27Nmj1NRU1axZ0+q+GzZssHz+Bw4cUKtWraz6vPV7lJXC8J3u2rWrKleurKpVq+qJJ57QwoULlZiYaNXG09NTkjIcBwAAuFNsO9cDAJBvxYoVyzCl05bSfwHNiaurq9V7k8lkmZKZmdKlS1umhqbz9/fX2bNnrY6lv/f3989VHLnVs2dPVa5cWZ9++qkCAwNlNptVv359y7puTZs21bFjx/TTTz9p7dq16tu3r7p06aJvvvlGCQkJCggIyLDmlST5+vpme9+b85S+Ltetx7LLW34kJCSoZ8+eeuuttzKcCwgIyFef/v7+GYqpKSkpunTpUo6fVXx8vHr06CFvb299++23Gb47N3vqqaespgYGBgZm2/f06dP173//W2vXrrUqAtladt/3nPJtNputClvZFY6dnJxkGIbVsZvXYsttPM7Oztq5c6dVQU6SihcvnuW9c6swfKe9vb21a9cuRUREaM2aNZo4caImTZqkHTt2WP7Opk8DLlOmjE1jBQAAyC2KbQBQiGzbtk0DBgywet+kSRNJUp06dbRgwQJdvXrVMrpt8+bNcnJyUq1ateTt7a2goCCtW7dOnTp1sllMTZo00f79+62OBQcHa8KECUpOTrb8sv7zzz+rVq1aVps+5Mbu3bt17do1S7Fw27ZtKl68uCpWrKiLFy8qOjpan376qUJCQiRJmzZtytCHj4+P+vXrp379+qlPnz7q0aOHLl26pKZNmyo2NlYuLi7ZrgF2u3x8fBQYGKjNmzerQ4cOluObN29Wy5YtJaV9fv/5z390/fp1y0igbdu2WfXTtGlT/fe//1VQUJDN1kYLDg7W5cuXtXPnTjVr1kyS9Msvv2QoJN0qLi5O3bt3l7u7u1asWJHj6EY/Pz+rddeyM23aNE2ZMkWrV6/OsB7gnZSbfHt7e2c45ubmptTUVKtjZcqUUWxsrAzDsBSyoqKi8hRPkyZNlJqaqnPnzlm+77eqU6dOhrX2bv0e2YI9v9MuLi7q0qWLunTporCwMPn6+uqXX37Rww8/LCltw4UKFSqodOnStnhUAACAPGMaKQA4iBs3big2NtbqdeuOfEuXLtW8efN08OBBhYWFKTIy0rIBQmhoqDw8PDRw4EDt3btX69ev1//93//piSeesEwJmzRpkt555x3NnDlThw4d0q5du/TBBx/cVtzdu3fX1q1brYoLjz32mNzc3DR06FDt27dPS5Ys0fvvv6+xY8da2kRGRqp27do6ffp0tv0nJSVp6NCh2r9/v1auXKmwsDCNHj1aTk5OKlmypEqVKqVPPvlEhw8f1i+//GJ1D0l69913tWjRIv355586ePCgli5dKn9/f/n6+qpLly4KDg5Wr169tGbNGh0/flxbtmzRhAkT9Ntvv91WXm71wgsv6K233tKSJUsUHR2tl19+WVFRUXrmmWcsOTOZTBo+fLjlWadPn27Vx6hRo3Tp0iX1799fO3bs0JEjR7R69WoNHjw4Q3Ent+rUqaMePXpo+PDhioyM1ObNmzV69Gg9+uijltFnp0+fVu3atRUZGSkprdDWrVs3Xb16VXPnzlVcXJzlO5vfONK99dZbeu211zRv3jwFBQVZ+r15V91Zs2blOB3aFvKb76CgIP366686ffq05e9wx44ddf78eU2bNk1HjhzRhx9+qJ9++ilP8dSsWVOhoaEaMGCAli1bpmPHjikyMlJTp07Vjz/+KEkaM2aMVq1apenTp+vQoUOaNWtWhh1CbcUe3+kffvhBM2fOVFRUlE6cOKEvvvhCZrNZtWrVsrTZuHGjunXrViDPDAAAkBsU2wDAQaxatUoBAQFWr3bt2lm1CQ8P1+LFi9WwYUN98cUXWrRokerWrStJ8vLy0urVq3Xp0iW1aNFCffr00T333KNZs2ZZrh84cKBmzJihjz76SPXq1dMDDzxg2Tkwv+699165uLho7dq1lmMlSpTQmjVrdOzYMTVr1kzPP/+8Jk6cqBEjRljaJCYmKjo6OtOpdDe75557VKNGDbVv3179+vXTgw8+aFkbzMnJSYsXL9bOnTtVv359Pffcc3r77betrvf29ta0adPUvHlztWjRQsePH9fKlSvl5OQkk8mklStXqn379ho8eLBq1qypRx99VCdOnLAUKG1lzJgxGjt2rJ5//nk1aNBAq1at0ooVK1SjRg1JadMAv//+e+3Zs0dNmjTRhAkTMkytSx9JlJqaqm7duqlBgwZ69tln5evrKyenzH+k57RzpyQtXLhQtWvX1j333KP77rtP7dq10yeffGI5n5ycrOjoaMsaWLt27dL27du1Z88eVa9e3eo7m76WXn7Nnj1bSUlJ6tOnj1W/NxdpLly4cEfWqMtPviVp8uTJOn78uKpVq2aZylinTh199NFH+vDDD9WoUSNFRkZm2JkzN+bPn68BAwbo+eefV61atdSrVy/t2LFDlSpVkiS1bt1an376qd5//301atRIa9as0auvvpq/BOTAHt9pX19fLVu2TJ07d1adOnU0Z84cLVq0SPXq1ZMkXb9+XcuXL9fw4cML5JkBAAByw2TcuoAIAMAhmUwmffvtt+rVq5e9Q8ngww8/1IoVK7R69Wp7h4JbDBw4UCaTSQsWLLB3KECBmz17tr799lurjVAAAADuNNZsAwDctieffFKXL19WfHx8pmtYwT4Mw1BERESm69gBdyNXV9fbnhoPAABwuxjZBgCFhCOPbAMAAAAApGFkGwAUEvy3EQAAAABwfGyQAAAAAAAAANgIxTYAAAAAAADARii2AQAAAAAAADZCsQ0AAAAAAACwEYptAAAAAAAAgI1QbAMAAAAAAABshGIbAAAAAAAAYCMU2wAAAAAAAAAb+X93ftg1ApxpugAAAABJRU5ErkJggg==","text/plain":["
"]},"metadata":{},"output_type":"display_data"}],"source":["plot_perf(model_perf_dfs, model_markers)"]}],"metadata":{"accelerator":"GPU","application/vnd.databricks.v1+notebook":{"dashboards":[],"environmentMetadata":null,"language":"python","notebookMetadata":{"mostRecentlyExecutedCommandWithImplicitDF":{"commandId":-1,"dataframes":["_sqldf"]},"pythonIndentUnit":4},"notebookName":"10_eval-lf-medium-py3.11","widgets":{}},"colab":{"gpuType":"L4","provenance":[]},"kernelspec":{"display_name":"Python 3","name":"python3"},"language_info":{"codemirror_mode":{"name":"ipython","version":3},"file_extension":".py","mimetype":"text/x-python","name":"python","nbconvert_exporter":"python","pygments_lexer":"ipython3","version":"3.11.9"}},"nbformat":4,"nbformat_minor":0}